d2l.bib

@InProceedings{	  Abadi.Barham.Chen.ea.2016,
  title		= {Tensorflow: A system for large-scale machine learning},
  author	= {Abadi, Mart{\'\i}n and Barham, Paul and Chen, Jianmin and
		  Chen, Zhifeng and Davis, Andy and Dean, Jeffrey and Devin,
		  Matthieu and Ghemawat, Sanjay and Irving, Geoffrey and
		  Isard, Michael and others},
  booktitle	= {12th $\{$USENIX$\}$ symposium on operating systems design
		  and implementation ($\{$OSDI$\}$ 16)},
  pages		= {265--283},
  year		= {2016}
}

@Article{	  Abdel-Hamid.Mohamed.Jiang.ea.2014,
  title		= {Convolutional neural networks for speech recognition},
  author	= {Abdel-Hamid, Ossama and Mohamed, Abdel-rahman and Jiang,
		  Hui and Deng, Li and Penn, Gerald and Yu, Dong},
  journal	= {IEEE/ACM Transactions on audio, speech, and language
		  processing},
  volume	= {22},
  number	= {10},
  pages		= {1533--1545},
  year		= {2014},
  publisher	= {IEEE}
}

@InProceedings{	  Ahmed.Aly.Gonzalez.ea.2012,
  title		= {Scalable inference in latent variable models},
  author	= {Ahmed, Amr and Aly, Moahmed and Gonzalez, Joseph and
		  Narayanamurthy, Shravan and Smola, Alexander J},
  booktitle	= {Proceedings of the fifth ACM international conference on
		  Web search and data mining},
  pages		= {123--132},
  year		= {2012},
  organization	= {ACM}
}

@book{guyon2008feature,
  title={Feature extraction: foundations and applications},
  author={Guyon, Isabelle and Gunn, Steve and Nikravesh, Masoud and Zadeh, Lofti A},
  volume={207},
  year={2008},
  publisher={Springer}
}

@Article{	  Aji.McEliece.2000,
  title		= {The generalized distributive law},
  author	= {Aji, Srinivas M and McEliece, Robert J},
  journal	= {IEEE transactions on Information Theory},
  volume	= {46},
  number	= {2},
  pages		= {325--343},
  year		= {2000},
  publisher	= {IEEE}
}

@Article{	  Alsallakh.Kokhlikyan.Miglani.ea.2020,
  title		= {Mind the Pad--CNNs can Develop Blind Spots},
  author	= {Alsallakh, Bilal and Kokhlikyan, Narine and Miglani, Vivek
		  and Yuan, Jun and Reblitz-Richardson, Orion},
  journal	= {arXiv preprint arXiv:2010.02178},
  year		= {2020}
}

@Article{	  Aronszajn.1950,
  title		= {Theory of reproducing kernels},
  author	= {Aronszajn, Nachman},
  journal	= {Transactions of the American mathematical society},
  volume	= {68},
  number	= {3},
  pages		= {337--404},
  year		= {1950}
}

@Article{	  Ba.Kiros.Hinton.2016,
  title		= {Layer normalization},
  author	= {Ba, Jimmy Lei and Kiros, Jamie Ryan and Hinton, Geoffrey
		  E},
  journal	= {arXiv preprint arXiv:1607.06450},
  year		= {2016}
}

@Article{	  Bahdanau.Cho.Bengio.2014,
  title		= {Neural machine translation by jointly learning to align
		  and translate},
  author	= {Bahdanau, Dzmitry and Cho, Kyunghyun and Bengio, Yoshua},
  journal	= {arXiv preprint arXiv:1409.0473},
  year		= {2014}
}

@Article{	  Bartlett.Montanari.Rakhlin.2021,
  title		= {Deep learning: a statistical viewpoint},
  author	= {Bartlett, Peter L and Montanari, Andrea and Rakhlin,
		  Alexander},
  journal	= {arXiv preprint arXiv:2103.09177},
  year		= {2021}
}

@InProceedings{	  Bay.Tuytelaars.Van-Gool.2006,
  title		= {Surf: Speeded up robust features},
  author	= {Bay, Herbert and Tuytelaars, Tinne and Van Gool, Luc},
  booktitle	= {European conference on computer vision},
  pages		= {404--417},
  year		= {2006},
  organization	= {Springer}
}

@Article{	  Bengio.Ducharme.Vincent.ea.2003,
  title		= {A neural probabilistic language model},
  author	= {Bengio, Yoshua and Ducharme, R{\'e}jean and Vincent,
		  Pascal and Jauvin, Christian},
  journal	= {Journal of machine learning research},
  volume	= {3},
  number	= {Feb},
  pages		= {1137--1155},
  year		= {2003}
}

@article{bengio1994learning,
  title={Learning long-term dependencies with gradient descent is difficult},
  author={Bengio, Yoshua and Simard, Patrice and Frasconi, Paolo},
  journal={IEEE transactions on neural networks},
  volume={5},
  number={2},
  pages={157--166},
  year={1994},
  publisher={IEEE}
}


@InProceedings{	  Bergstra.Breuleux.Bastien.ea.2010,
  title		= {Theano: A CPU and GPU math compiler in Python},
  author	= {Bergstra, James and Breuleux, Olivier and Bastien,
		  Fr{\'e}d{\'e}ric and Lamblin, Pascal and Pascanu, Razvan
		  and Desjardins, Guillaume and Turian, Joseph and
		  Warde-Farley, David and Bengio, Yoshua},
  booktitle	= {Proc. 9th python in science conf},
  volume	= {1},
  pages		= {3--10},
  year		= {2010}
}

@InProceedings{	  Beutel.Murray.Faloutsos.ea.2014,
  title		= {Cobafi: collaborative bayesian filtering},
  author	= {Beutel, Alex and Murray, Kenton and Faloutsos, Christos
		  and Smola, Alexander J},
  booktitle	= {Proceedings of the 23rd international conference on World
		  wide web},
  pages		= {97--108},
  year		= {2014}
}

@Article{	  Bishop.1995,
  title		= {Training with noise is equivalent to Tikhonov
		  regularization},
  author	= {Bishop, Chris M},
  journal	= {Neural computation},
  volume	= {7},
  number	= {1},
  pages		= {108--116},
  year		= {1995},
  publisher	= {MIT Press}
}

@Book{		  Bishop.2006,
  title		= {Pattern recognition and machine learning},
  author	= {Bishop, Christopher M},
  year		= {2006},
  publisher	= {springer}
}

@Article{	  Black.Scholes.1973,
  title		= {The Pricing of Options and Corporate Liabilities},
  author	= {Black, Fischer and Scholes, Myron},
  journal	= {The Journal of Political Economy},
  pages		= {637--654},
  year		= {1973},
  publisher	= {JSTOR}
}

@InProceedings{	  Bodla.Singh.Chellappa.ea.2017,
  title		= {Soft-NMS--improving object detection with one line of
		  code},
  author	= {Bodla, Navaneeth and Singh, Bharat and Chellappa, Rama and
		  Davis, Larry S},
  booktitle	= {Proceedings of the IEEE international conference on
		  computer vision},
  pages		= {5561--5569},
  year		= {2017}
}

@Article{	  Bojanowski.Grave.Joulin.ea.2017,
  title		= {Enriching word vectors with subword information},
  author	= {Bojanowski, Piotr and Grave, Edouard and Joulin, Armand
		  and Mikolov, Tomas},
  journal	= {Transactions of the Association for Computational
		  Linguistics},
  volume	= {5},
  pages		= {135--146},
  year		= {2017},
  publisher	= {MIT Press}
}

@Book{		  Bollobas.1999,
  title		= {Linear analysis},
  author	= {Bollob{\'a}s, B},
  year		= {1999},
  publisher	= {Cambridge University Press, Cambridge}
}

@InCollection{	  Bottou.2010,
  title		= {Large-scale machine learning with stochastic gradient
		  descent},
  author	= {Bottou, L{\'e}on},
  booktitle	= {Proceedings of COMPSTAT'2010},
  pages		= {177--186},
  year		= {2010},
  publisher	= {Springer}
}

@InProceedings{	  Bottou.Le-Cun.1988,
  author	= {Bottou, {L\'eon} and {Le Cun}, Yann},
  title		= {SN: A Simulator for Connectionist Models},
  pages		= {371-382},
  booktitle	= {Proceedings of NeuroNimes 88},
  address	= {Nimes, France},
  year		= {1988},
  url		= {http://leon.bottou.org/papers/bottou-lecun-88}
}

@Article{	  Boucheron.Bousquet.Lugosi.2005,
  title		= {Theory of classification: A survey of some recent
		  advances},
  author	= {Boucheron, St{\'e}phane and Bousquet, Olivier and Lugosi,
		  G{\'a}bor},
  journal	= {ESAIM: probability and statistics},
  volume	= {9},
  pages		= {323--375},
  year		= {2005},
  publisher	= {EDP Sciences}
}

@Article{	  Bowman.Angeli.Potts.ea.2015,
  title		= {A large annotated corpus for learning natural language
		  inference},
  author	= {Bowman, Samuel R and Angeli, Gabor and Potts, Christopher
		  and Manning, Christopher D},
  journal	= {arXiv preprint arXiv:1508.05326},
  year		= {2015}
}

@Book{		  Boyd.Vandenberghe.2004,
  address	= {Cambridge, England},
  author	= {Stephen Boyd and Lieven Vandenberghe},
  publisher	= {Cambridge University Press},
  title		= {Convex Optimization},
  year		= 2004
}

@Article{	  Bradley.Terry.1952,
  title		= {Rank analysis of incomplete block designs: I. The method
		  of paired comparisons},
  author	= {Bradley, Ralph Allan and Terry, Milton E},
  journal	= {Biometrika},
  volume	= {39},
  number	= {3/4},
  pages		= {324--345},
  year		= {1952},
  publisher	= {JSTOR}
}

@InProceedings{	  Brown.Cocke.Della-Pietra.ea.1988,
  title		= {A statistical approach to language translation},
  author	= {Brown, Peter F and Cocke, John and Della Pietra, Stephen A
		  and Della Pietra, Vincent J and Jelinek, Frederick and
		  Mercer, Robert L and Roossin, Paul},
  booktitle	= {Coling Budapest 1988 Volume 1: International Conference on
		  Computational Linguistics},
  year		= {1988}
}

@Article{	  Brown.Cocke.Della-Pietra.ea.1990,
  title		= {A statistical approach to machine translation},
  author	= {Brown, Peter F and Cocke, John and Della Pietra, Stephen A
		  and Della Pietra, Vincent J and Jelinek, Frederick and
		  Lafferty, John and Mercer, Robert L and Roossin, Paul S},
  journal	= {Computational linguistics},
  volume	= {16},
  number	= {2},
  pages		= {79--85},
  year		= {1990}
}

@InProceedings{	  Brown.Sandholm.2017,
  title		= {Libratus: The Superhuman AI for No-Limit Poker.},
  author	= {Brown, Noam and Sandholm, Tuomas},
  booktitle	= {IJCAI},
  pages		= {5226--5228},
  year		= {2017}
}

@Article{	  Buslaev.Iglovikov.Khvedchenya.ea.2020,
  title		= {Albumentations: fast and flexible image augmentations},
  author	= {Buslaev, Alexander and Iglovikov, Vladimir I and
		  Khvedchenya, Eugene and Parinov, Alex and Druzhinin,
		  Mikhail and Kalinin, Alexandr A},
  journal	= {Information},
  volume	= {11},
  number	= {2},
  pages		= {125},
  year		= {2020},
  publisher	= {Multidisciplinary Digital Publishing Institute}
}

@Book{		  Cajal.Azoulay.1894,
  title		= {Les nouvelles id{\'e}es sur la structure du syst{\`e}me
		  nerveux chez l'homme et chez les vert{\'e}br{\'e}s},
  author	= {y Cajal, Santiago Ram{\'o}n and Azoulay, L{\'e}on},
  year		= {1894},
  publisher	= {C. Reinwald}
}

@Article{	  Campbell.Hoane-Jr.Hsu.2002,
  title		= {Deep blue},
  author	= {Campbell, Murray and Hoane Jr, A Joseph and Hsu,
		  Feng-hsiung},
  journal	= {Artificial intelligence},
  volume	= {134},
  number	= {1-2},
  pages		= {57--83},
  year		= {2002},
  publisher	= {Elsevier}
}

@InCollection{	  Canny.1987,
  title		= {A computational approach to edge detection},
  author	= {Canny, John},
  booktitle	= {Readings in computer vision},
  pages		= {184--203},
  year		= {1987},
  publisher	= {Elsevier}
}

@Article{	  Cantelli.1933,
  author	= {F.~P. Cantelli},
  journal	= {Rend.\ Accad.\ Lincei},
  number	= 1,
  pages		= 39,
  title		= {Sulla probabilita come limita della frequenza},
  volume	= 26,
  year		= 1933
}

@InProceedings{	  Cer.Diab.Agirre.ea.2017,
  title		= {SemEval-2017 Task 1: Semantic Textual Similarity
		  Multilingual and Crosslingual Focused Evaluation},
  author	= {Cer, Daniel and Diab, Mona and Agirre, Eneko and
		  Lopez-Gazpio, I{\~n}igo and Specia, Lucia},
  booktitle	= {Proceedings of the 11th International Workshop on Semantic
		  Evaluation (SemEval-2017)},
  pages		= {1--14},
  year		= {2017}
}

@Article{	  Chen.Li.Li.ea.2015,
  title		= {Mxnet: A flexible and efficient machine learning library
		  for heterogeneous distributed systems},
  author	= {Chen, Tianqi and Li, Mu and Li, Yutian and Lin, Min and
		  Wang, Naiyan and Wang, Minjie and Xiao, Tianjun and Xu,
		  Bing and Zhang, Chiyuan and Zhang, Zheng},
  journal	= {arXiv preprint arXiv:1512.01274},
  year		= {2015}
}

@InProceedings{	  Cheng.Dong.Lapata.2016,
  title		= {Long Short-Term Memory-Networks for Machine Reading},
  author	= {Cheng, Jianpeng and Dong, Li and Lapata, Mirella},
  booktitle	= {Proceedings of the 2016 Conference on Empirical Methods in
		  Natural Language Processing},
  pages		= {551--561},
  year		= {2016}
}

@Article{	  Chetlur.Woolley.Vandermersch.ea.2014,
  title		= {cudnn: Efficient primitives for deep learning},
  author	= {Chetlur, Sharan and Woolley, Cliff and Vandermersch,
		  Philippe and Cohen, Jonathan and Tran, John and Catanzaro,
		  Bryan and Shelhamer, Evan},
  journal	= {arXiv preprint arXiv:1410.0759},
  year		= {2014}
}

@Article{	  Cho.Van-Merrienboer.Bahdanau.ea.2014,
  title		= {On the properties of neural machine translation:
		  Encoder-decoder approaches},
  author	= {Cho, Kyunghyun and Van Merri{\"e}nboer, Bart and Bahdanau,
		  Dzmitry and Bengio, Yoshua},
  journal	= {arXiv preprint arXiv:1409.1259},
  year		= {2014}
}

@Article{	  Cho.Van-Merrienboer.Gulcehre.ea.2014,
  title		= {Learning phrase representations using RNN encoder-decoder
		  for statistical machine translation},
  author	= {Cho, Kyunghyun and Van Merri{\"e}nboer, Bart and Gulcehre,
		  Caglar and Bahdanau, Dzmitry and Bougares, Fethi and
		  Schwenk, Holger and Bengio, Yoshua},
  journal	= {arXiv preprint arXiv:1406.1078},
  year		= {2014}
}

@Book{		  Chowdhury.2010,
  title		= {Introduction to modern information retrieval},
  author	= {Chowdhury, Gobinda G},
  year		= {2010},
  publisher	= {Facet publishing}
}

@Article{	  Chung.Gulcehre.Cho.ea.2014,
  title		= {Empirical evaluation of gated recurrent neural networks on
		  sequence modeling},
  author	= {Chung, Junyoung and Gulcehre, Caglar and Cho, KyungHyun
		  and Bengio, Yoshua},
  journal	= {arXiv preprint arXiv:1412.3555},
  year		= {2014}
}

@Article{	  Collobert.Weston.Bottou.ea.2011,
  title		= {Natural language processing (almost) from scratch},
  author	= {Collobert, Ronan and Weston, Jason and Bottou, L{\'e}on
		  and Karlen, Michael and Kavukcuoglu, Koray and Kuksa,
		  Pavel},
  journal	= {Journal of machine learning research},
  volume	= {12},
  number	= {ARTICLE},
  pages		= {2493--2537},
  year		= {2011}
}

@Article{	  Corfield.Scholkopf.Vapnik.2009,
  title		= {Falsificationism and statistical learning theory:
		  Comparing the Popper and Vapnik-Chervonenkis dimensions},
  author	= {Corfield, David and Sch{\"o}lkopf, Bernhard and Vapnik,
		  Vladimir},
  journal	= {Journal for General Philosophy of Science},
  volume	= {40},
  number	= {1},
  pages		= {51--58},
  year		= {2009},
  publisher	= {Springer}
}

@Book{		  Cover.Thomas.1999,
  title		= {Elements of information theory},
  author	= {T. Cover and J.M. Thomas},
  year		= {1999},
  publisher	= {John Wiley \& Sons}
}

@Article{	  Cramer.1946,
  title		= {Mathematical methods of statistics.},
  author	= {Cram{\'e}r, H},
  journal	= {Mathematical methods of statistics.},
  year		= {1946},
  publisher	= {Princeton University Press}
}

@Article{	  Csiszar.2008,
  title		= {Axiomatic characterizations of information measures},
  author	= {Csisz{\'a}r, Imre},
  journal	= {Entropy},
  volume	= {10},
  number	= {3},
  pages		= {261--273},
  year		= {2008},
  publisher	= {Molecular Diversity Preservation International}
}

@Article{	  Cybenko.1989,
  title		= {Approximation by superpositions of a sigmoidal function},
  author	= {Cybenko, George},
  journal	= {Mathematics of control, signals and systems},
  volume	= {2},
  number	= {4},
  pages		= {303--314},
  year		= {1989},
  publisher	= {Springer}
}

@InProceedings{	  Dalal.Triggs.2005,
  title		= {Histograms of oriented gradients for human detection},
  author	= {Dalal, Navneet and Triggs, Bill},
  booktitle	= {2005 IEEE computer society conference on computer vision
		  and pattern recognition (CVPR'05)},
  volume	= {1},
  pages		= {886--893},
  year		= {2005},
  organization	= {IEEE}
}

@Article{	  De-Cock.2011,
  title		= {Ames, Iowa: Alternative to the Boston housing data as an
		  end of semester regression project},
  author	= {De Cock, Dean},
  journal	= {Journal of Statistics Education},
  volume	= {19},
  number	= {3},
  year		= {2011},
  publisher	= {Taylor \& Francis}
}

@Article{	  De-Valois.Albrecht.Thorell.1982,
  title		= {Spatial frequency selectivity of cells in macaque visual
		  cortex},
  author	= {De Valois, Russell L and Albrecht, Duane G and Thorell,
		  Lisa G},
  journal	= {Vision research},
  volume	= {22},
  number	= {5},
  pages		= {545--559},
  year		= {1982},
  publisher	= {Elsevier}
}

@InProceedings{	  DeCandia.Hastorun.Jampani.ea.2007,
  title		= {Dynamo: Amazon's highly available key-value store},
  author	= {DeCandia, Giuseppe and Hastorun, Deniz and Jampani, Madan
		  and Kakulapati, Gunavardhan and Lakshman, Avinash and
		  Pilchin, Alex and Sivasubramanian, Swaminathan and
		  Vosshall, Peter and Vogels, Werner},
  booktitle	= {ACM SIGOPS operating systems review},
  volume	= {41},
  number	= {6},
  pages		= {205--220},
  year		= {2007},
  organization	= {ACM}
}

@InProceedings{	  Dean.Corrado.Monga.ea.2012,
  title		= {Large scale distributed deep networks},
  author	= {Dean, Jeffrey and Corrado, Greg S and Monga, Rajat and
		  Chen, Kai and Devin, Matthieu and Le, Quoc V and Mao, Mark
		  Z and Ranzato, Marc'Aurelio and Senior, Andrew and Tucker,
		  Paul and others},
  booktitle	= {Proceedings of the 25th International Conference on Neural
		  Information Processing Systems-Volume 1},
  pages		= {1223--1231},
  year		= {2012}
}

@InProceedings{	  Deng.Dong.Socher.ea.2009,
  title		= {Imagenet: A large-scale hierarchical image database},
  author	= {Deng, Jia and Dong, Wei and Socher, Richard and Li, Li-Jia
		  and Li, Kai and Fei-Fei, Li},
  booktitle	= {2009 IEEE conference on computer vision and pattern
		  recognition},
  pages		= {248--255},
  year		= {2009},
  organization	= {Ieee}
}

@Article{	  Der-Kiureghian.Ditlevsen.2009,
  title		= {Aleatory or epistemic? Does it matter?},
  author	= {Der Kiureghian, Armen and Ditlevsen, Ove},
  journal	= {Structural safety},
  volume	= {31},
  number	= {2},
  pages		= {105--112},
  year		= {2009},
  publisher	= {Elsevier}
}

@Article{	  Devlin.Chang.Lee.ea.2018,
  title		= {Bert: Pre-training of deep bidirectional transformers for
		  language understanding},
  author	= {Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and
		  Toutanova, Kristina},
  journal	= {arXiv preprint arXiv:1810.04805},
  year		= {2018}
}

@InProceedings{	  Doersch.Gupta.Efros.2015,
  title		= {Unsupervised visual representation learning by context
		  prediction},
  author	= {Doersch, Carl and Gupta, Abhinav and Efros, Alexei A},
  booktitle	= {Proceedings of the IEEE international conference on
		  computer vision},
  pages		= {1422--1430},
  year		= {2015}
}

@InProceedings{	  Dosovitskiy.Beyer.Kolesnikov.ea.2021,
  title		= {An Image is Worth 16x16 Words: Transformers for Image
		  Recognition at Scale},
  author	= {Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov,
		  Alexander and Weissenborn, Dirk and Zhai, Xiaohua and
		  Unterthiner, Thomas and Dehghani, Mostafa and Minderer,
		  Matthias and Heigold, Georg and Gelly, Sylvain and others},
  booktitle	= {International Conference on Learning Representations},
  year		= {2021}
}

@InProceedings{	  Dosovitskiy.Beyer.Kolesnikov.ea.2021*1,
  title		= {An image is worth 16x16 words: Transformers for image
		  recognition at scale},
  author	= {Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov,
		  Alexander and Weissenborn, Dirk and Zhai, Xiaohua and
		  Unterthiner, Thomas and Dehghani, Mostafa and Minderer,
		  Matthias and Heigold, Georg and Gelly, Sylvain and others},
  booktitle	= {International Conference on Learning Representations},
  year		= {2021}
}

@InCollection{	  Doucet.De-Freitas.Gordon.2001,
  title		= {An introduction to sequential Monte Carlo methods},
  author	= {Doucet, Arnaud and De Freitas, Nando and Gordon, Neil},
  booktitle	= {Sequential Monte Carlo methods in practice},
  pages		= {3--14},
  year		= {2001},
  publisher	= {Springer}
}

@Article{	  Duchi.Hazan.Singer.2011,
  title		= {Adaptive subgradient methods for online learning and
		  stochastic optimization},
  author	= {Duchi, John and Hazan, Elad and Singer, Yoram},
  journal	= {Journal of Machine Learning Research},
  volume	= {12},
  number	= {Jul},
  pages		= {2121--2159},
  year		= {2011}
}

@Article{	  Dumoulin.Visin.2016,
  title		= {A guide to convolution arithmetic for deep learning},
  author	= {Dumoulin, Vincent and Visin, Francesco},
  journal	= {arXiv preprint arXiv:1603.07285},
  year		= {2016}
}

@Article{	  Edelman.Ostrovsky.Schwarz.2007,
  title		= {Internet advertising and the generalized second-price
		  auction: Selling billions of dollars worth of keywords},
  author	= {Edelman, Benjamin and Ostrovsky, Michael and Schwarz,
		  Michael},
  journal	= {American economic review},
  volume	= {97},
  number	= {1},
  pages		= {242--259},
  year		= {2007}
}

@article{elman1990finding,
  title={Finding structure in time},
  author={Elman, Jeffrey L},
  journal={Cognitive science},
  volume={14},
  number={2},
  pages={179--211},
  year={1990},
  publisher={Wiley Online Library}
}


@Book{		  Fechner.1860,
  title		= {Elemente der Ppsychophysik},
  author	= {Fechner, Gustav Theodor},
  volume	= {2},
  year		= {1860},
  publisher	= {Breitkopf u. H{\"a}rtel}
}

@Book{		  Fernando.2004,
  title		= {GPU gems: programming techniques, tips, and tricks for
		  real-time graphics},
  author	= {Fernando, Randima},
  volume	= {590},
  year		= {2004},
  publisher	= {Addison-Wesley Reading}
}

@Article{	  Field.1987,
  title		= {Relations between the statistics of natural images and the
		  response properties of cortical cells},
  author	= {Field, David J},
  journal	= {Josa a},
  volume	= {4},
  number	= {12},
  pages		= {2379--2394},
  year		= {1987},
  publisher	= {Optical Society of America}
}

@Book{		  Fisher.1928,
  title		= {Statistical methods for research workers.},
  author	= {Fisher, RA},
  year		= {1928},
  publisher	= {Stechert}
}

@InProceedings{	  Flammarion.Bach.2015,
  title		= {From averaging to acceleration, there is only a
		  step-size},
  author	= {Flammarion, Nicolas and Bach, Francis},
  booktitle	= {Conference on Learning Theory},
  pages		= {658--695},
  year		= {2015}
}

@Article{	  Frankle.Carbin.2018,
  title		= {The lottery ticket hypothesis: Finding sparse, trainable
		  neural networks},
  author	= {Frankle, Jonathan and Carbin, Michael},
  journal	= {arXiv preprint arXiv:1803.03635},
  year		= {2018}
}

@Article{	  Frazier.2018,
  title		= {A tutorial on Bayesian optimization},
  author	= {Frazier, Peter I},
  journal	= {arXiv preprint arXiv:1807.02811},
  year		= {2018}
}

@InProceedings{	  Freund.Schapire.ea.1996,
  title		= {Experiments with a new boosting algorithm},
  author	= {Freund, Yoav and Schapire, Robert E and others},
  booktitle	= {icml},
  volume	= {96},
  pages		= {148--156},
  year		= {1996},
  organization	= {Citeseer}
}

@Article{	  Friedman.1997,
  title		= {On bias, variance, 0/1—loss, and the
		  curse-of-dimensionality},
  author	= {Friedman, Jerome H},
  journal	= {Data mining and knowledge discovery},
  volume	= {1},
  number	= {1},
  pages		= {55--77},
  year		= {1997},
  publisher	= {Springer}
}

@Article{	  Frostig.Johnson.Leary.2018,
  title		= {Compiling machine learning programs via high-level
		  tracing},
  author	= {Frostig, Roy and Johnson, Matthew James and Leary, Chris},
  journal	= {Systems for Machine Learning},
  year		= {2018}
}

@InCollection{	  Fukushima.1982,
  title		= {Neocognitron: A self-organizing neural network model for a
		  mechanism of visual pattern recognition},
  author	= {Fukushima, Kunihiko},
  booktitle	= {Competition and cooperation in neural nets},
  pages		= {267--285},
  year		= {1982},
  publisher	= {Springer}
}

@InProceedings{Gardner.Pleiss.Weinberger.Bindel.Wilson.2018,
  title={{GPyTorch}: Blackbox matrix-matrix {G}aussian process inference with {GPU} acceleration},
  author={Gardner, Jacob and Pleiss, Geoff and Weinberger, Kilian Q and Bindel, David and Wilson, Andrew G},
  booktitle={Advances in Neural Information Processing Systems},
  volume={31},
  year={2018}
}


@InProceedings{Garg.Balakrishnan.Kolter.Lipton.2021,
  title={Ratt: Leveraging unlabeled data to guarantee generalization},
  author={Garg, Saurabh and Balakrishnan, Sivaraman and Kolter, Zico and Lipton, Zachary},
  booktitle={International Conference on Machine Learning},
  pages={3598--3609},
  year={2021},
  organization={PMLR}
}


@InProceedings{	  Gatys.Ecker.Bethge.2016,
  title		= {Image style transfer using convolutional neural networks},
  author	= {Gatys, Leon A and Ecker, Alexander S and Bethge,
		  Matthias},
  booktitle	= {Proceedings of the IEEE conference on computer vision and
		  pattern recognition},
  pages		= {2414--2423},
  year		= {2016}
}

@Article{	  Gauss.1809,
  title		= {Theoria motus corporum coelestum},
  author	= {Gauss, Carl Friedrich},
  journal	= {Werke},
  year		= {1809}
}

@Article{	  Gibbs.1902,
  title		= {Elementary Principles of Statistical Mechanics},
  author	= {Gibbs, Josiah Willard},
  journal	= {Compare},
  volume	= {289},
  pages		= {314},
  year		= {1902}
}

@Article{	  Ginibre.1965,
  title		= {Statistical ensembles of complex, quaternion, and real
		  matrices},
  author	= {Ginibre, Jean},
  journal	= {Journal of Mathematical Physics},
  volume	= {6},
  number	= {3},
  pages		= {440--449},
  year		= {1965},
  publisher	= {AIP}
}

@InProceedings{	  Girshick.2015,
  title		= {Fast r-cnn},
  author	= {Girshick, Ross},
  booktitle	= {Proceedings of the IEEE international conference on
		  computer vision},
  pages		= {1440--1448},
  year		= {2015}
}

@InProceedings{	  Girshick.Donahue.Darrell.ea.2014,
  title		= {Rich feature hierarchies for accurate object detection and
		  semantic segmentation},
  author	= {Girshick, Ross and Donahue, Jeff and Darrell, Trevor and
		  Malik, Jitendra},
  booktitle	= {Proceedings of the IEEE conference on computer vision and
		  pattern recognition},
  pages		= {580--587},
  year		= {2014}
}

@Article{	  Glivenko.1933,
  author	= {V.~I. Glivenko},
  journal	= {Giornale dell'Istituta Italiano degli Attuari},
  pages		= 92,
  title		= {Sulla determinazione empirica delle leggi di probabilita},
  volume	= 4,
  year		= 1933
}

@InProceedings{	  Glorot.Bengio.2010,
  title		= {Understanding the difficulty of training deep feedforward
		  neural networks},
  author	= {Glorot, Xavier and Bengio, Yoshua},
  booktitle	= {Proceedings of the thirteenth international conference on
		  artificial intelligence and statistics},
  pages		= {249--256},
  year		= {2010}
}

@Article{	  Goh.2017,
  author	= {Goh, Gabriel},
  title		= {Why Momentum Really Works},
  journal	= {Distill},
  year		= {2017},
  url		= {http://distill.pub/2017/momentum},
  doi		= {10.23915/distill.00006}
}

@Article{	  Goldberg.Nichols.Oki.ea.1992,
  title		= {Using collaborative filtering to weave an information
		  tapestry},
  author	= {Goldberg, David and Nichols, David and Oki, Brian M and
		  Terry, Douglas},
  journal	= {Communications of the ACM},
  volume	= {35},
  number	= {12},
  pages		= {61--71},
  year		= {1992},
  publisher	= {Association for Computing Machinery, Inc.}
}

@Misc{		  Golub.Van-Loan.1996,
  title		= {Matrix computations. Johns Hopkins studies in the
		  mathematical sciences},
  author	= {Golub, Gene H and Van Loan, Charles F},
  year		= {1996},
  publisher	= {Johns Hopkins University Press, Baltimore, MD,}
}

@Book{		  Goodfellow.Bengio.Courville.2016,
  title		= {Deep Learning},
  author	= {Ian Goodfellow and Yoshua Bengio and Aaron Courville},
  publisher	= {MIT Press},
  note		= {\url{http://www.deeplearningbook.org}},
  year		= {2016}
}

@InProceedings{	  Goodfellow.Pouget-Abadie.Mirza.ea.2014,
  title		= {Generative adversarial nets},
  author	= {Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi
		  and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and
		  Courville, Aaron and Bengio, Yoshua},
  booktitle	= {Advances in neural information processing systems},
  pages		= {2672--2680},
  year		= {2014}
}

@Article{	  Gotmare.Keskar.Xiong.ea.2018,
  title		= {A Closer Look at Deep Learning Heuristics: Learning rate
		  restarts, Warmup and Distillation},
  author	= {Gotmare, Akhilesh and Keskar, Nitish Shirish and Xiong,
		  Caiming and Socher, Richard},
  journal	= {arXiv preprint arXiv:1810.13243},
  year		= {2018}
}

@Article{	  Goyal.Bochkovskiy.Deng.ea.2021,
  title		= {Non-deep Networks},
  author	= {Goyal, Ankit and Bochkovskiy, Alexey and Deng, Jia and
		  Koltun, Vladlen},
  journal	= {arXiv preprint arXiv:2110.07641},
  year		= {2021}
}

@Article{	  Graham.2014,
  title		= {Fractional max-pooling},
  author	= {Graham, Benjamin},
  journal	= {arXiv preprint arXiv:1412.6071},
  year		= {2014}
}

@Article{	  Graves.2013,
  title		= {Generating sequences with recurrent neural networks},
  author	= {Graves, Alex},
  journal	= {arXiv preprint arXiv:1308.0850},
  year		= {2013}
}

@Article{	  Graves.Schmidhuber.2005,
  title		= {Framewise phoneme classification with bidirectional LSTM
		  and other neural network architectures},
  author	= {Graves, Alex and Schmidhuber, J{\"u}rgen},
  journal	= {Neural networks},
  volume	= {18},
  number	= {5-6},
  pages		= {602--610},
  year		= {2005},
  publisher	= {Elsevier}
}

@article{graves2008novel,
  title={A novel connectionist system for unconstrained handwriting recognition},
  author={Graves, Alex and Liwicki, Marcus and Fern{\'a}ndez, Santiago and Bertolami, Roman and Bunke, Horst and Schmidhuber, J{\"u}rgen},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  volume={31},
  number={5},
  pages={855--868},
  year={2008},
  publisher={IEEE}
}

@Article{	  Griewank.1989,
  title		= {On automatic differentiation},
  author	= {Griewank, Andreas},
  journal	= {Mathematical Programming: recent developments and
		  applications},
  volume	= {6},
  number	= {6},
  pages		= {83--107},
  year		= {1989},
  publisher	= {Citeseer}
}

@InCollection{	  Gunawardana.Shani.2015,
  title		= {Evaluating recommender systems},
  author	= {Gunawardana, Asela and Shani, Guy},
  booktitle	= {Recommender systems handbook},
  pages		= {265--308},
  year		= {2015},
  publisher	= {Springer}
}

@InProceedings{	  Guo.Tang.Ye.ea.2017,
  title		= {DeepFM: a factorization-machine based neural network for
		  CTR prediction},
  author	= {Guo, Huifeng and Tang, Ruiming and Ye, Yunming and Li,
		  Zhenguo and He, Xiuqiang},
  booktitle	= {Proceedings of the 26th International Joint Conference on
		  Artificial Intelligence},
  pages		= {1725--1731},
  year		= {2017},
  organization	= {AAAI Press}
}

@Article{	  Hadjis.Zhang.Mitliagkas.ea.2016,
  title		= {Omnivore: An optimizer for multi-device deep learning on
		  cpus and gpus},
  author	= {Hadjis, Stefan and Zhang, Ce and Mitliagkas, Ioannis and
		  Iter, Dan and R{\'e}, Christopher},
  journal	= {arXiv preprint arXiv:1606.04487},
  year		= {2016}
}

@Book{		  Hartley.Zisserman.2000,
  author	= {Hartley, Richard and Zisserman, Andrew},
  title		= {Multiple View Geometry in Computer Vision},
  year		= {2000},
  publisher	= {Cambridge University Press}
}

@InProceedings{	  Hazan.Rakhlin.Bartlett.2008,
  title		= {Adaptive online gradient descent},
  author	= {Hazan, Elad and Rakhlin, Alexander and Bartlett, Peter L},
  booktitle	= {Advances in Neural Information Processing Systems},
  pages		= {65--72},
  year		= {2008}
}

@InProceedings{	  He.Chua.2017,
  title		= {Neural factorization machines for sparse predictive
		  analytics},
  author	= {He, Xiangnan and Chua, Tat-Seng},
  booktitle	= {Proceedings of the 40th International ACM SIGIR conference
		  on Research and Development in Information Retrieval},
  pages		= {355--364},
  year		= {2017},
  organization	= {ACM}
}

@InProceedings{	  He.Gkioxari.Dollar.ea.2017,
  title		= {Mask r-cnn},
  author	= {He, Kaiming and Gkioxari, Georgia and Doll{\'a}r, Piotr
		  and Girshick, Ross},
  booktitle	= {Proceedings of the IEEE international conference on
		  computer vision},
  pages		= {2961--2969},
  year		= {2017}
}

@InProceedings{	  He.Liao.Zhang.ea.2017,
  title		= {Neural collaborative filtering},
  author	= {He, Xiangnan and Liao, Lizi and Zhang, Hanwang and Nie,
		  Liqiang and Hu, Xia and Chua, Tat-Seng},
  booktitle	= {Proceedings of the 26th international conference on world
		  wide web},
  pages		= {173--182},
  year		= {2017},
  organization	= {International World Wide Web Conferences Steering
		  Committee}
}

@InProceedings{	  He.Zhang.Ren.ea.2015,
  title		= {Delving deep into rectifiers: Surpassing human-level
		  performance on imagenet classification},
  author	= {He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun,
		  Jian},
  booktitle	= {Proceedings of the IEEE international conference on
		  computer vision},
  pages		= {1026--1034},
  year		= {2015}
}

@InProceedings{	  He.Zhang.Ren.ea.2016,
  title		= {Deep residual learning for image recognition},
  author	= {He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun,
		  Jian},
  booktitle	= {Proceedings of the IEEE conference on computer vision and
		  pattern recognition},
  pages		= {770--778},
  year		= {2016}
}

@InProceedings{	  He.Zhang.Ren.ea.2016*1,
  title		= {Identity mappings in deep residual networks},
  author	= {He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun,
		  Jian},
  booktitle	= {European conference on computer vision},
  pages		= {630--645},
  year		= {2016},
  organization	= {Springer}
}

@Book{		  Hebb.Hebb.1949,
  title		= {The organization of behavior},
  author	= {Hebb, Donald Olding and Hebb, DO},
  volume	= {65},
  year		= {1949},
  publisher	= {Wiley New York}
}

@Article{	  Hendrycks.Gimpel.2016,
  title		= {Gaussian error linear units (gelus)},
  author	= {Hendrycks, Dan and Gimpel, Kevin},
  journal	= {arXiv preprint arXiv:1606.08415},
  year		= {2016}
}

@Article{	  Henighan.Kaplan.Katz.ea.2020,
  title		= {Scaling laws for autoregressive generative modeling},
  author	= {Henighan, Tom and Kaplan, Jared and Katz, Mor and Chen,
		  Mark and Hesse, Christopher and Jackson, Jacob and Jun,
		  Heewoo and Brown, Tom B and Dhariwal, Prafulla and Gray,
		  Scott and others},
  journal	= {arXiv preprint arXiv:2010.14701},
  year		= {2020}
}

@Book{		  Hennessy.Patterson.2011,
  title		= {Computer architecture: a quantitative approach},
  author	= {Hennessy, John L and Patterson, David A},
  year		= {2011},
  publisher	= {Elsevier}
}

@InProceedings{	  Herlocker.Konstan.Borchers.ea.1999,
  title		= {An algorithmic framework for performing collaborative
		  filtering},
  author	= {Herlocker, Jonathan L and Konstan, Joseph A and Borchers,
		  Al and Riedl, John},
  booktitle	= {22nd Annual International ACM SIGIR Conference on Research
		  and Development in Information Retrieval, SIGIR 1999},
  pages		= {230--237},
  year		= {1999},
  organization	= {Association for Computing Machinery, Inc}
}

@Article{	  Hidasi.Karatzoglou.Baltrunas.ea.2015,
  title		= {Session-based recommendations with recurrent neural
		  networks},
  author	= {Hidasi, Bal{\'a}zs and Karatzoglou, Alexandros and
		  Baltrunas, Linas and Tikk, Domonkos},
  journal	= {arXiv preprint arXiv:1511.06939},
  year		= {2015}
}

@Misc{		  Hochreiter.Bengio.Frasconi.ea.2001,
  title		= {Gradient flow in recurrent nets: the difficulty of
		  learning long-term dependencies},
  author	= {Hochreiter, Sepp and Bengio, Yoshua and Frasconi, Paolo
		  and Schmidhuber, J{\"u}rgen and others},
  year		= {2001},
  publisher	= {A field guide to dynamical recurrent neural networks. IEEE
		  Press}
}

@Article{	  Hochreiter.Schmidhuber.1997,
  title		= {Long short-term memory},
  author	= {Hochreiter, Sepp and Schmidhuber, J{\"u}rgen},
  journal	= {Neural computation},
  volume	= {9},
  number	= {8},
  pages		= {1735--1780},
  year		= {1997},
  publisher	= {MIT Press}
}

@InProceedings{	  Howard.Sandler.Chu.ea.2019,
  title		= {Searching for mobilenetv3},
  author	= {Howard, Andrew and Sandler, Mark and Chu, Grace and Chen,
		  Liang-Chieh and Chen, Bo and Tan, Mingxing and Wang, Weijun
		  and Zhu, Yukun and Pang, Ruoming and Vasudevan, Vijay and
		  Le, Quoc V. and Adam, Hartwig},
  booktitle	= {Proceedings of the IEEE/CVF International Conference on
		  Computer Vision},
  pages		= {1314--1324},
  year		= {2019}
}

@InProceedings{	  Hoyer.Janzing.Mooij.ea.2009,
  title		= {Nonlinear causal discovery with additive noise models},
  author	= {Hoyer, Patrik O and Janzing, Dominik and Mooij, Joris M
		  and Peters, Jonas and Sch{\"o}lkopf, Bernhard},
  booktitle	= {Advances in neural information processing systems},
  pages		= {689--696},
  year		= {2009}
}

@InProceedings{	  Hu.Koren.Volinsky.2008,
  title		= {Collaborative filtering for implicit feedback datasets},
  author	= {Hu, Yifan and Koren, Yehuda and Volinsky, Chris},
  booktitle	= {2008 Eighth IEEE International Conference on Data Mining},
  pages		= {263--272},
  year		= {2008},
  organization	= {Ieee}
}

@article{10.1145/3544903.3544906,
  author = {Hu, Zhiqiang and Lee, Roy Ka-Wei and Aggarwal, Charu C. and Zhang, Aston},
  title = {Text Style Transfer: A Review and Experimental Evaluation},
  year = {2022},
  issue_date = {June 2022},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  volume = {24},
  number = {1},
  issn = {1931-0145},
  url = {https://doi.org/10.1145/3544903.3544906},
  doi = {10.1145/3544903.3544906},
  abstract = {The stylistic properties of text have intrigued computational linguistics researchers in recent years. Specifically, researchers have investigated the text style transfer task (TST), which aims to change the stylistic properties of the text while retaining its independent content of style. Over the last few years, many novel TST algorithms have been developed, while the industry has leveraged these algorithms to enable exciting TST applications. The field of TST research has developed because of this symbiosis. This article aims to provide a comprehensive review of recent research efforts on text style transfer. More concretely, we create a taxonomy to organize the TST models, and provide a comprehensive summary of the state of the art. We review existing evaluation methodologies for TST tasks and conduct a large-scale reproducibility study in which we experimentally benchmark 19 state-of-the-art TST algorithms on two publicly available datasets. Finally, we expand on current trends and provide new perspectives on the new and exciting developments in the TST field.},
  journal = {SIGKDD Explor. Newsl.},
  month = {jun},
  pages = {14–45},
  numpages = {32}
}

@article{parzen1957consistent,
  title={On consistent estimates of the spectrum of a stationary time series},
  author={Parzen, Emanuel},
  journal={The Annals of Mathematical Statistics},
  pages={329--348},
  year={1957},
  publisher={JSTOR}
}

@article{mack1982weak,
  title={Weak and strong uniform consistency of kernel regression estimates},
  author={Mack, Yue-pok and Silverman, Bernard W},
  journal={Zeitschrift f{\"u}r Wahrscheinlichkeitstheorie und verwandte Gebiete},
  volume={61},
  number={3},
  pages={405--415},
  year={1982},
  publisher={Springer}
}

@book{Silverman86,
  Address =	 {London},
  Author =	 {B.~W. Silverman},
  Publisher =	 {Chapman and Hall},
  Series =	 {Monographs on statistics and applied probability},
  Title =	 {Density Estimation for Statistical and Data
                  Analysis},
  Year =	 1986
}

@article{norelli2022asif,
  title={ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training},
  author={Norelli, Antonio and Fumero, Marco and Maiorca, Valentino and Moschella, Luca and Rodol{\`a}, Emanuele and Locatello, Francesco},
  journal={arXiv preprint arXiv:2210.01738},
  year={2022}
}

@InProceedings{	  Hu.Shen.Sun.2018,
  title		= {Squeeze-and-excitation networks},
  author	= {Hu, Jie and Shen, Li and Sun, Gang},
  booktitle	= {Proceedings of the IEEE conference on computer vision and
		  pattern recognition},
  pages		= {7132--7141},
  year		= {2018}
}

@InProceedings{	  Huang.Liu.Van-Der-Maaten.ea.2017,
  title		= {Densely connected convolutional networks},
  author	= {Huang, Gao and Liu, Zhuang and Van Der Maaten, Laurens and
		  Weinberger, Kilian Q},
  booktitle	= {Proceedings of the IEEE conference on computer vision and
		  pattern recognition},
  pages		= {4700--4708},
  year		= {2017}
}

@Article{	  Huang.Xu.Yu.2015,
  title		= {Bidirectional LSTM-CRF models for sequence tagging},
  author	= {Huang, Zhiheng and Xu, Wei and Yu, Kai},
  journal	= {arXiv preprint arXiv:1508.01991},
  year		= {2015}
}

@Article{	  Hubel.Wiesel.1959,
  title		= {Receptive fields of single neurones in the cat's striate
		  cortex},
  author	= {Hubel, David H and Wiesel, Torsten N},
  journal	= {The Journal of physiology},
  volume	= {148},
  number	= {3},
  pages		= {574--591},
  year		= {1959},
  publisher	= {Wiley Online Library}
}

@Article{	  Hubel.Wiesel.1962,
  title		= {Receptive fields, binocular interaction and functional
		  architecture in the cat's visual cortex},
  author	= {Hubel, David H and Wiesel, Torsten N},
  journal	= {The Journal of physiology},
  volume	= {160},
  number	= {1},
  pages		= {106--154},
  year		= {1962},
  publisher	= {Wiley Online Library}
}

@Article{	  Hubel.Wiesel.1968,
  title		= {Receptive fields and functional architecture of monkey
		  striate cortex},
  author	= {Hubel, David H and Wiesel, Torsten N},
  journal	= {The Journal of physiology},
  volume	= {195},
  number	= {1},
  pages		= {215--243},
  year		= {1968},
  publisher	= {Wiley Online Library}
}

@InProceedings{	  Ioffe.2017,
  title		= {Batch renormalization: Towards reducing minibatch
		  dependence in batch-normalized models},
  author	= {Ioffe, Sergey},
  booktitle	= {Advances in neural information processing systems},
  pages		= {1945--1953},
  year		= {2017}
}

@Article{	  Ioffe.Szegedy.2015,
  title		= {Batch normalization: Accelerating deep network training by
		  reducing internal covariate shift},
  author	= {Ioffe, Sergey and Szegedy, Christian},
  journal	= {arXiv preprint arXiv:1502.03167},
  year		= {2015}
}

@Article{	  Izmailov.Podoprikhin.Garipov.ea.2018,
  title		= {Averaging weights leads to wider optima and better
		  generalization},
  author	= {Izmailov, Pavel and Podoprikhin, Dmitrii and Garipov,
		  Timur and Vetrov, Dmitry and Wilson, Andrew Gordon},
  journal	= {arXiv preprint arXiv:1803.05407},
  year		= {2018}
}

@InProceedings{Jacot.Grabriel.Hongler.2018,
  title={Neural tangent kernel: Convergence and generalization in neural networks},
  author={Jacot, Arthur and Gabriel, Franck and Hongler, Cl{\'e}ment},
  booktitle={Advances in neural information processing systems},
  volume={31},
  year={2018}
}


@Book{		  Jaeger.2002,
  title		= {Tutorial on training recurrent neural networks, covering
		  BPPT, RTRL, EKF and the" echo state network" approach},
  author	= {Jaeger, Herbert},
  volume	= {5},
  year		= {2002},
  publisher	= {GMD-Forschungszentrum Informationstechnik Bonn}
}

@Book{		  James.2007,
  title		= {The principles of psychology},
  author	= {James, William},
  volume	= {1},
  year		= {2007},
  publisher	= {Cosimo, Inc.}
}

@InProceedings{	  Jia.Shelhamer.Donahue.ea.2014,
  title		= {Caffe: Convolutional architecture for fast feature
		  embedding},
  author	= {Jia, Yangqing and Shelhamer, Evan and Donahue, Jeff and
		  Karayev, Sergey and Long, Jonathan and Girshick, Ross and
		  Guadarrama, Sergio and Darrell, Trevor},
  booktitle	= {Proceedings of the 22nd ACM international conference on
		  Multimedia},
  pages		= {675--678},
  year		= {2014}
}

@Article{	  Jia.Song.He.ea.2018,
  title		= {Highly scalable deep learning training system with
		  mixed-precision: Training imagenet in four minutes},
  author	= {Jia, Xianyan and Song, Shutao and He, Wei and Wang,
		  Yangzihao and Rong, Haidong and Zhou, Feihu and Xie,
		  Liqiang and Guo, Zhenyu and Yang, Yuanzhou and Yu, Liwei
		  and others},
  journal	= {arXiv preprint arXiv:1807.11205},
  year		= {2018}
}

@InProceedings{	  Jouppi.Young.Patil.ea.2017,
  title		= {In-datacenter performance analysis of a tensor processing
		  unit},
  author	= {Jouppi, Norman P and Young, Cliff and Patil, Nishant and
		  Patterson, David and Agrawal, Gaurav and Bajwa, Raminder
		  and Bates, Sarah and Bhatia, Suresh and Boden, Nan and
		  Borchers, Al and others},
  booktitle	= {2017 ACM/IEEE 44th Annual International Symposium on
		  Computer Architecture (ISCA)},
  pages		= {1--12},
  year		= {2017},
  organization	= {IEEE}
}

@Article{	  Kalchbrenner.Grefenstette.Blunsom.2014,
  title		= {A convolutional neural network for modelling sentences},
  author	= {Kalchbrenner, Nal and Grefenstette, Edward and Blunsom,
		  Phil},
  journal	= {arXiv preprint arXiv:1404.2188},
  year		= {2014}
}

@InProceedings{	  Kalman.Kwasny.1992,
  title		= {Why tanh: choosing a sigmoidal function},
  author	= {Kalman, Barry L and Kwasny, Stan C},
  booktitle	= {[Proceedings 1992] IJCNN International Joint Conference on
		  Neural Networks},
  volume	= {4},
  pages		= {578--581},
  year		= {1992},
  organization	= {IEEE}
}

@Article{	  Karras.Aila.Laine.ea.2017,
  title		= {Progressive growing of gans for improved quality,
		  stability, and variation},
  author	= {Karras, Tero and Aila, Timo and Laine, Samuli and
		  Lehtinen, Jaakko},
  journal	= {arXiv preprint arXiv:1710.10196},
  year		= {2017}
}

@Article{	  Kawaguchi.Kaelbling.Bengio.2017,
  title		= {Generalization in deep learning},
  author	= {Kawaguchi, Kenji and Kaelbling, Leslie Pack and Bengio,
		  Yoshua},
  journal	= {arXiv preprint arXiv:1710.05468},
  year		= {2017}
}

@Article{	  Kim.2014,
  title		= {Convolutional neural networks for sentence
		  classification},
  author	= {Kim, Yoon},
  journal	= {arXiv preprint arXiv:1408.5882},
  year		= {2014}
}

@Article{	  Kimeldorf.Wahba.1971,
  author	= {G.~S.~Kimeldorf and G.~Wahba},
  journal	= {J.~Math.~Anal.~Appl.},
  pages		= {82-95},
  title		= {Some Results on {T}chebycheffian Spline Functions},
  volume	= 33,
  year		= 1971
}

@Article{	  Kingma.Ba.2014,
  title		= {Adam: A method for stochastic optimization},
  author	= {Kingma, Diederik P and Ba, Jimmy},
  journal	= {arXiv preprint arXiv:1412.6980},
  year		= {2014}
}

@inproceedings{Kingma.Welling.2014,
  author = {Kingma, Diederik P. and Welling, Max},
  booktitle = {International Conference on Learning Representations ({ICLR})},
  title = {{Auto-Encoding Variational Bayes}},
  year = 2014
}



@Article{	  Kipf.Welling.2016,
  title		= {Semi-supervised classification with graph convolutional
		  networks},
  author	= {Kipf, Thomas N and Welling, Max},
  journal	= {arXiv preprint arXiv:1609.02907},
  year		= {2016}
}

@Book{		  Koller.Friedman.2009,
  title		= {Probabilistic graphical models: principles and
		  techniques},
  author	= {Koller, Daphne and Friedman, Nir},
  year		= {2009},
  publisher	= {MIT press}
}

@Article{	  Kolmogorov.1933,
  title		= {Sulla determinazione empirica di una lgge di
		  distribuzione},
  author	= {Kolmogorov, Andrey},
  journal	= {Inst. Ital. Attuari, Giorn.},
  volume	= {4},
  pages		= {83--91},
  year		= {1933}
}

@Article{	  Kolter.2008,
  title		= {Linear Algebra Review and Reference},
  author	= {Kolter, Zico},
  journal	= {Available online:
		  http://cs229.stanford.edu/section/cs229-linalg.pdf},
  year		= {2008}
}

@InProceedings{	  Koren.2009,
  title		= {Collaborative filtering with temporal dynamics},
  author	= {Koren, Yehuda},
  booktitle	= {Proceedings of the 15th ACM SIGKDD international
		  conference on Knowledge discovery and data mining},
  pages		= {447--456},
  year		= {2009},
  organization	= {ACM}
}

@Article{	  Koren.Bell.Volinsky.2009,
  title		= {Matrix factorization techniques for recommender systems},
  author	= {Koren, Yehuda and Bell, Robert and Volinsky, Chris},
  journal	= {Computer},
  number	= {8},
  pages		= {30--37},
  year		= {2009},
  publisher	= {IEEE}
}

@InProceedings{	  Krizhevsky.Sutskever.Hinton.2012,
  title		= {Imagenet classification with deep convolutional neural
		  networks},
  author	= {Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey
		  E},
  booktitle	= {Advances in neural information processing systems},
  pages		= {1097--1105},
  year		= {2012}
}

@InProceedings{	  Krogh.Hertz.1992,
  title		= {A simple weight decay can improve generalization},
  author	= {Krogh, Anders and Hertz, John A},
  booktitle	= {Advances in neural information processing systems},
  pages		= {950--957},
  year		= {1992}
}

@Article{	  Kung.1988,
  title		= {VLSI array processors},
  author	= {Kung, Sun Yuan},
  journal	= {Englewood Cliffs, NJ, Prentice Hall, 1988, 685 p. Research
		  supported by the Semiconductor Research Corp., SDIO, NSF,
		  and US Navy.},
  year		= {1988}
}

@Article{	  Kuzovkin.Vicente.Petton.ea.2018,
  title		= {Activations of deep convolutional neural networks are
		  aligned with gamma band activity of human visual cortex},
  author	= {Kuzovkin, Ilya and Vicente, Raul and Petton, Mathilde and
		  Lachaux, Jean-Philippe and Baciu, Monica and Kahane,
		  Philippe and Rheims, Sylvain and Vidal, Juan R and Aru,
		  Jaan},
  journal	= {Communications biology},
  volume	= {1},
  number	= {1},
  pages		= {1--12},
  year		= {2018},
  publisher	= {Nature Publishing Group}
}

@Article{	  LeCun.Bengio.ea.1995,
  title		= {Convolutional networks for images, speech, and time
		  series},
  author	= {LeCun, Yann and Bengio, Yoshua and others},
  journal	= {The handbook of brain theory and neural networks},
  volume	= {3361},
  number	= {10},
  pages		= {1995},
  year		= {1995}
}

@Article{	  LeCun.Boser.Denker.ea.1989,
  title		= {Backpropagation applied to handwritten zip code
		  recognition},
  author	= {LeCun, Yann and Boser, Bernhard and Denker, John S and
		  Henderson, Donnie and Howard, Richard E and Hubbard, Wayne
		  and Jackel, Lawrence D},
  journal	= {Neural computation},
  volume	= {1},
  number	= {4},
  pages		= {541--551},
  year		= {1989},
  publisher	= {MIT Press}
}

@Article{	  LeCun.Bottou.Bengio.ea.1998,
  title		= {Gradient-based learning applied to document recognition},
  author	= {LeCun, Yann and Bottou, L{\'e}on and Bengio, Yoshua and
		  Haffner, Patrick and others},
  journal	= {Proceedings of the IEEE},
  volume	= {86},
  number	= {11},
  pages		= {2278--2324},
  year		= {1998},
  publisher	= {Taipei, Taiwan}
}

@Article{	  LeCun.Bottou.Orr.ea.1998,
  title		= {Efficient backprop},
  author	= {LeCun, Yann and Bottou, Leon and Orr, G and Muller,
		  Klaus-Robert},
  journal	= {Neural Networks: Tricks of the Trade. New York: Springer},
  year		= {1998}
}

@InProceedings{	  LeCun.Jackel.Bottou.ea.1995,
  title		= {Comparison of learning algorithms for handwritten digit
		  recognition},
  author	= {LeCun, Yann and Jackel, LD and Bottou, Leon and Brunot, A
		  and Cortes, Corinna and Denker, John and Drucker, Harris
		  and Guyon, Isabelle and Muller, UA and Sackinger, Eduard
		  and others},
  booktitle	= {International conference on artificial neural networks},
  volume	= {60},
  pages		= {53--60},
  year		= {1995},
  organization	= {Perth, Australia}
}

@Book{		  Legendre.1805,
  title		= {M{\'e}moire sur les op{\'e}rations trigonom{\'e}triques:
		  dont les r{\'e}sultats d{\'e}pendent de la figure de la terre},
  author	= {Legendre, Adrien Marie},
  number	= {1},
  year		= {1805},
  publisher	= {F. Didot}
}

@PhDThesis{	  Li.2017,
  title		= {Scaling Distributed Machine Learning with System and
		  Algorithm Co-design},
  author	= {Li, Mu},
  year		= {2017},
  school	= {PhD Thesis, CMU}
}

@InProceedings{	  Li.Andersen.Park.ea.2014,
  title		= {Scaling distributed machine learning with the parameter
		  server},
  author	= {Li, Mu and Andersen, David G and Park, Jun Woo and Smola,
		  Alexander J and Ahmed, Amr and Josifovski, Vanja and Long,
		  James and Shekita, Eugene J and Su, Bor-Yiing},
  booktitle	= {11th $\{$USENIX$\}$ Symposium on Operating Systems Design
		  and Implementation ($\{$OSDI$\}$ 14)},
  pages		= {583--598},
  year		= {2014}
}

@InProceedings{	  Li.Zhang.Chen.ea.2014,
  title		= {Efficient mini-batch training for stochastic
		  optimization},
  author	= {Li, Mu and Zhang, Tong and Chen, Yuqiang and Smola,
		  Alexander J},
  booktitle	= {Proceedings of the 20th ACM SIGKDD international
		  conference on Knowledge discovery and data mining},
  pages		= {661--670},
  year		= {2014}
}

@Article{	  Lin.Chen.Yan.2013,
  title		= {Network in network},
  author	= {Lin, Min and Chen, Qiang and Yan, Shuicheng},
  journal	= {arXiv preprint arXiv:1312.4400},
  year		= {2013}
}

@Article{	  Lin.Feng.Santos.ea.2017,
  title		= {A structured self-attentive sentence embedding},
  author	= {Lin, Zhouhan and Feng, Minwei and Santos, Cicero Nogueira
		  dos and Yu, Mo and Xiang, Bing and Zhou, Bowen and Bengio,
		  Yoshua},
  journal	= {arXiv preprint arXiv:1703.03130},
  year		= {2017}
}

@InProceedings{	  Lin.Goyal.Girshick.ea.2017,
  title		= {Focal loss for dense object detection},
  author	= {Lin, Tsung-Yi and Goyal, Priya and Girshick, Ross and He,
		  Kaiming and Doll{\'a}r, Piotr},
  booktitle	= {Proceedings of the IEEE international conference on
		  computer vision},
  pages		= {2980--2988},
  year		= {2017}
}

@Article{	  Lin.Lv.Zhu.ea.2010,
  title		= {Imagenet classification: fast descriptor coding and
		  large-scale svm training},
  author	= {Lin, Yuanqing and Lv, F and Zhu, S and Yang, M and Cour, T
		  and Yu, K and Cao, L and Li, Z and Tsai, MH and Zhou, X and
		  others},
  journal	= {Large scale visual recognition challenge},
  year		= {2010}
}

@InProceedings{Lipton.Kale.2016,
  title={Learning to diagnose with LSTM recurrent neural networks},
  author={Lipton, Zachary C and Kale, David C and Elkan, Charles and Wetzel, Randall},
  booktitle={International Conference on Learning Representations (ICLR)},
  year={2016}
}


@Article{	  Lipton.Steinhardt.2018,
  title		= {Troubling trends in machine learning scholarship},
  author	= {Lipton, Zachary C and Steinhardt, Jacob},
  journal	= {Communications of the ACM (CACM)},
  year		= {2018}
}

@article{     Lipton.Berkowitz.Elkan.2015,
  title		= {A critical review of recurrent neural networks for sequence learning},
  author	= {Lipton, Zachary C and Berkowitz, John and Elkan, Charles},
  journal	= {arXiv preprint arXiv:1506.00019},
  year		= {2015}
}


@InProceedings{	  Liu.Anguelov.Erhan.ea.2016,
  title		= {Ssd: Single shot multibox detector},
  author	= {Liu, Wei and Anguelov, Dragomir and Erhan, Dumitru and
		  Szegedy, Christian and Reed, Scott and Fu, Cheng-Yang and
		  Berg, Alexander C},
  booktitle	= {European conference on computer vision},
  pages		= {21--37},
  year		= {2016},
  organization	= {Springer}
}

@Article{	  Liu.Nocedal.1989,
  title		= {On the limited memory BFGS method for large scale
		  optimization},
  author	= {Liu, Dong C and Nocedal, Jorge},
  journal	= {Mathematical programming},
  volume	= {45},
  number	= {1},
  pages		= {503--528},
  year		= {1989},
  publisher	= {Springer}
}

@Article{	  Liu.Ott.Goyal.ea.2019,
  title		= {Roberta: A robustly optimized bert pretraining approach},
  author	= {Liu, Yinhan and Ott, Myle and Goyal, Naman and Du, Jingfei
		  and Joshi, Mandar and Chen, Danqi and Levy, Omer and Lewis,
		  Mike and Zettlemoyer, Luke and Stoyanov, Veselin},
  journal	= {arXiv preprint arXiv:1907.11692},
  year		= {2019}
}

@InProceedings{	  Long.Shelhamer.Darrell.2015,
  title		= {Fully convolutional networks for semantic segmentation},
  author	= {Long, Jonathan and Shelhamer, Evan and Darrell, Trevor},
  booktitle	= {Proceedings of the IEEE conference on computer vision and
		  pattern recognition},
  pages		= {3431--3440},
  year		= {2015}
}

@Article{	  Loshchilov.Hutter.2016,
  title		= {Sgdr: Stochastic gradient descent with warm restarts},
  author	= {Loshchilov, Ilya and Hutter, Frank},
  journal	= {arXiv preprint arXiv:1608.03983},
  year		= {2016}
}

@Article{	  Lowe.2004,
  title		= {Distinctive image features from scale-invariant
		  keypoints},
  author	= {Lowe, David G},
  journal	= {International journal of computer vision},
  volume	= {60},
  number	= {2},
  pages		= {91--110},
  year		= {2004},
  publisher	= {Springer}
}

@Article{	  Luo.Wang.Shao.ea.2018,
  title		= {Towards understanding regularization in batch
		  normalization},
  author	= {Luo, Ping and Wang, Xinjiang and Shao, Wenqi and Peng,
		  Zhanglin},
  journal	= {arXiv preprint},
  year		= {2018}
}

@InProceedings{	  Maas.Daly.Pham.ea.2011,
  title		= {Learning word vectors for sentiment analysis},
  author	= {Maas, Andrew L and Daly, Raymond E and Pham, Peter T and
		  Huang, Dan and Ng, Andrew Y and Potts, Christopher},
  booktitle	= {Proceedings of the 49th annual meeting of the association
		  for computational linguistics: Human language
		  technologies-volume 1},
  pages		= {142--150},
  year		= {2011},
  organization	= {Association for Computational Linguistics}
}

@Article{	  Mangasarian.1965,
  author	= {O.~L.~Mangasarian},
  journal	= {Oper. Res.},
  pages		= {444-452},
  title		= {Linear and Nonlinear Separation of Patterns by Linear
		  Programming},
  volume	= 13,
  year		= 1965
}

@Article{	  Mangram.2013,
  title		= {A simplified perspective of the Markowitz portfolio
		  theory},
  author	= {Mangram, Myles E},
  journal	= {Global journal of business research},
  volume	= {7},
  number	= {1},
  pages		= {59--70},
  year		= {2013}
}

@InProceedings{	  McCann.Bradbury.Xiong.ea.2017,
  title		= {Learned in translation: Contextualized word vectors},
  author	= {McCann, Bryan and Bradbury, James and Xiong, Caiming and
		  Socher, Richard},
  booktitle	= {Advances in Neural Information Processing Systems},
  pages		= {6294--6305},
  year		= {2017}
}

@Article{	  McCulloch.Pitts.1943,
  title		= {A logical calculus of the ideas immanent in nervous
		  activity},
  author	= {McCulloch, Warren S and Pitts, Walter},
  journal	= {The bulletin of mathematical biophysics},
  volume	= {5},
  number	= {4},
  pages		= {115--133},
  year		= {1943},
  publisher	= {Springer}
}

@InProceedings{	  McMahan.Holt.Sculley.ea.2013,
  title		= {Ad click prediction: a view from the trenches},
  author	= {McMahan, H Brendan and Holt, Gary and Sculley, David and
		  Young, Michael and Ebner, Dietmar and Grady, Julian and
		  Nie, Lan and Phillips, Todd and Davydov, Eugene and
		  Golovin, Daniel and others},
  booktitle	= {Proceedings of the 19th ACM SIGKDD international
		  conference on Knowledge discovery and data mining},
  pages		= {1222--1230},
  year		= {2013},
  organization	= {ACM}
}

@Article{	  Mead.1980,
  title		= {Introduction to VLSI systems},
  author	= {Mead, Carver},
  journal	= {IEE Proceedings I-Solid-State and Electron Devices},
  volume	= {128},
  number	= {1},
  pages		= {18},
  year		= {1980},
  publisher	= {IET}
}

@Article{	  Merity.Xiong.Bradbury.ea.2016,
  title		= {Pointer sentinel mixture models},
  author	= {Merity, Stephen and Xiong, Caiming and Bradbury, James and
		  Socher, Richard},
  journal	= {arXiv preprint arXiv:1609.07843},
  year		= {2016}
}

@Article{	  Micchelli.1986,
  author	= {C.~A.~Micchelli},
  journal	= {Proceedings of Symposia in Applied Mathematics},
  pages		= {81-102},
  title		= {Algebraic aspects of interpolation},
  volume	= 36,
  year		= 1986
}

@Article{	  Mikolov.Chen.Corrado.ea.2013,
  title		= {Efficient estimation of word representations in vector
		  space},
  author	= {Mikolov, Tomas and Chen, Kai and Corrado, Greg and Dean,
		  Jeffrey},
  journal	= {arXiv preprint arXiv:1301.3781},
  year		= {2013}
}

@InProceedings{	  Mikolov.Sutskever.Chen.ea.2013,
  title		= {Distributed representations of words and phrases and their
		  compositionality},
  author	= {Mikolov, Tomas and Sutskever, Ilya and Chen, Kai and
		  Corrado, Greg S and Dean, Jeff},
  booktitle	= {Advances in neural information processing systems},
  pages		= {3111--3119},
  year		= {2013}
}

@Article{	  Miller.1995,
  title		= {WordNet: a lexical database for English},
  author	= {Miller, George A},
  journal	= {Communications of the ACM},
  volume	= {38},
  number	= {11},
  pages		= {39--41},
  year		= {1995},
  publisher	= {ACM New York, NY, USA}
}

@InProceedings{	  Mirhoseini.Pham.Le.ea.2017,
  title		= {Device placement optimization with reinforcement
		  learning},
  author	= {Mirhoseini, Azalia and Pham, Hieu and Le, Quoc V and
		  Steiner, Benoit and Larsen, Rasmus and Zhou, Yuefeng and
		  Kumar, Naveen and Norouzi, Mohammad and Bengio, Samy and
		  Dean, Jeff},
  booktitle	= {Proceedings of the 34th International Conference on
		  Machine Learning-Volume 70},
  pages		= {2430--2439},
  year		= {2017},
  organization	= {JMLR. org}
}

@InProceedings{	  Mnih.Heess.Graves.ea.2014,
  title		= {Recurrent models of visual attention},
  author	= {Mnih, Volodymyr and Heess, Nicolas and Graves, Alex and
		  others},
  booktitle	= {Advances in neural information processing systems},
  pages		= {2204--2212},
  year		= {2014}
}

@InProceedings{	  Moon.Smola.Chang.ea.2010,
  title		= {Intervalrank: isotonic regression with listwise and
		  pairwise constraints},
  author	= {Moon, Taesup and Smola, Alex and Chang, Yi and Zheng,
		  Zhaohui},
  booktitle	= {Proceedings of the third ACM international conference on
		  Web search and data mining},
  pages		= {151--160},
  year		= {2010}
}

@Article{	  Morey.Hoekstra.Rouder.ea.2016,
  title		= {The fallacy of placing confidence in confidence
		  intervals},
  author	= {Morey, Richard D and Hoekstra, Rink and Rouder, Jeffrey N
		  and Lee, Michael D and Wagenmakers, Eric-Jan},
  journal	= {Psychonomic bulletin \& review},
  volume	= {23},
  number	= {1},
  pages		= {103--123},
  year		= {2016},
  publisher	= {Springer}
}

@Article{	  Murata.Yoshizawa.Amari.1994,
  title		= {Network information criterion-determining the number of
		  hidden units for an artificial neural network model},
  author	= {Murata, Noboru and Yoshizawa, Shuji and Amari, Shun-ichi},
  journal	= {IEEE transactions on neural networks},
  volume	= {5},
  number	= {6},
  pages		= {865--872},
  year		= {1994},
  publisher	= {IEEE}
}

@Article{	  Nadaraya.1964,
  title		= {On estimating regression},
  author	= {Nadaraya, Elizbar A},
  journal	= {Theory of Probability \& Its Applications},
  volume	= {9},
  number	= {1},
  pages		= {141--142},
  year		= {1964},
  publisher	= {SIAM}
}

@Article{	  Nagarajan.Kolter.2019,
  title		= {Uniform convergence may be unable to explain
		  generalization in deep learning},
  author	= {Nagarajan, Vaishnavh and Kolter, J Zico},
  journal	= {arXiv preprint arXiv:1902.04742},
  year		= {2019}
}

@InProceedings{	  Nair.Hinton.2010,
  title		= {Rectified linear units improve restricted boltzmann
		  machines},
  author	= {Nair, Vinod and Hinton, Geoffrey E},
  booktitle	= {Icml},
  year		= {2010}
}

@Article{	  Naor.Reingold.1999,
  title		= {On the Construction of Pseudorandom Permutations:
		  Luby—Rackoff Revisited},
  author	= {Naor, Moni and Reingold, Omer},
  journal	= {Journal of Cryptology},
  volume	= {12},
  number	= {1},
  pages		= {29--66},
  year		= {1999},
  publisher	= {Springer}
}

@Book{		  Nesterov.2018,
  title		= {Lectures on convex optimization},
  author	= {Nesterov, Yurii},
  volume	= {137},
  year		= {2018},
  publisher	= {Springer}
}

@Misc{		  Nesterov.Vial.2000,
  title		= {Confidence level solutions for stochastic programming,
		  Stochastic Programming E-Print Series},
  author	= {Nesterov, Yu and Vial, J-Ph},
  year		= {2000}
}

@Article{	  Neyman.1937,
  title		= {Outline of a theory of statistical estimation based on the
		  classical theory of probability},
  author	= {Neyman, Jerzy},
  journal	= {Philosophical Transactions of the Royal Society of London.
		  Series A, Mathematical and Physical Sciences},
  volume	= {236},
  number	= {767},
  pages		= {333--380},
  year		= {1937},
  publisher	= {The Royal Society London}
}

@Article{	  Ong.Smola.Williamson.ea.2005,
  title		= {Learning the kernel with hyperkernels},
  author	= {Ong, Cheng Soon and Smola, Alexander and Williamson,
		  Robert and others},
  year		= {2005},
  publisher	= {MIT Press},
  journal	= {Journal of Machine Learning Research}
}

@InProceedings{	  Papineni.Roukos.Ward.ea.2002,
  title		= {BLEU: a method for automatic evaluation of machine
		  translation},
  author	= {Papineni, Kishore and Roukos, Salim and Ward, Todd and
		  Zhu, Wei-Jing},
  booktitle	= {Proceedings of the 40th annual meeting of the Association
		  for Computational Linguistics},
  pages		= {311--318},
  year		= {2002}
}

@Article{	  Parikh.Tackstrom.Das.ea.2016,
  title		= {A decomposable attention model for natural language
		  inference},
  author	= {Parikh, Ankur P and T{\"a}ckstr{\"o}m, Oscar and Das,
		  Dipanjan and Uszkoreit, Jakob},
  journal	= {arXiv preprint arXiv:1606.01933},
  year		= {2016}
}

@InProceedings{	  Park.Liu.Wang.ea.2019,
  title		= {Semantic image synthesis with spatially-adaptive
		  normalization},
  author	= {Park, Taesung and Liu, Ming-Yu and Wang, Ting-Chun and
		  Zhu, Jun-Yan},
  booktitle	= {Proceedings of the IEEE Conference on Computer Vision and
		  Pattern Recognition},
  pages		= {2337--2346},
  year		= {2019}
}

@Article{	  Paszke.Gross.Massa.ea.2019,
  title		= {Pytorch: An imperative style, high-performance deep
		  learning library},
  author	= {Paszke, Adam and Gross, Sam and Massa, Francisco and
		  Lerer, Adam and Bradbury, James and Chanan, Gregory and
		  Killeen, Trevor and Lin, Zeming and Gimelshein, Natalia and
		  Antiga, Luca and others},
  journal	= {Advances in neural information processing systems},
  volume	= {32},
  pages		= {8026--8037},
  year		= {2019}
}

@Article{	  Paulus.Xiong.Socher.2017,
  title		= {A deep reinforced model for abstractive summarization},
  author	= {Paulus, Romain and Xiong, Caiming and Socher, Richard},
  journal	= {arXiv preprint arXiv:1705.04304},
  year		= {2017}
}

@InProceedings{	  Pennington.Schoenholz.Ganguli.2017,
  title		= {Resurrecting the sigmoid in deep learning through
		  dynamical isometry: theory and practice},
  author	= {Pennington, Jeffrey and Schoenholz, Samuel and Ganguli,
		  Surya},
  booktitle	= {Advances in neural information processing systems},
  pages		= {4785--4795},
  year		= {2017}
}

@InProceedings{	  Pennington.Socher.Manning.2014,
  title		= {Glove: Global vectors for word representation},
  author	= {Pennington, Jeffrey and Socher, Richard and Manning,
		  Christopher},
  booktitle	= {Proceedings of the 2014 conference on empirical methods in
		  natural language processing (EMNLP)},
  pages		= {1532--1543},
  year		= {2014}
}

@InProceedings{	  Peters.Ammar.Bhagavatula.ea.2017,
  title		= {Semi-supervised sequence tagging with bidirectional
		  language models},
  author	= {Peters, Matthew and Ammar, Waleed and Bhagavatula, Chandra
		  and Power, Russell},
  booktitle	= {Proceedings of the 55th Annual Meeting of the Association
		  for Computational Linguistics (Volume 1: Long Papers)},
  pages		= {1756--1765},
  year		= {2017}
}

@Book{		  Peters.Janzing.Scholkopf.2017,
  title		= {Elements of causal inference: foundations and learning
		  algorithms},
  author	= {Peters, Jonas and Janzing, Dominik and Sch{\"o}lkopf,
		  Bernhard},
  year		= {2017},
  publisher	= {MIT press}
}

@InProceedings{	  Peters.Neumann.Iyyer.ea.2018,
  title		= {Deep Contextualized Word Representations},
  author	= {Peters, Matthew and Neumann, Mark and Iyyer, Mohit and
		  Gardner, Matt and Clark, Christopher and Lee, Kenton and
		  Zettlemoyer, Luke},
  booktitle	= {Proceedings of the 2018 Conference of the North American
		  Chapter of the Association for Computational Linguistics:
		  Human Language Technologies, Volume 1 (Long Papers)},
  pages		= {2227--2237},
  year		= {2018}
}

@Article{	  Petersen.Pedersen.ea.2008,
  title		= {The matrix cookbook},
  author	= {Petersen, Kaare Brandt and Pedersen, Michael Syskind and
		  others},
  journal	= {Technical University of Denmark},
  volume	= {7},
  number	= {15},
  pages		= {510},
  year		= {2008}
}

@Article{	  Polyak.1964,
  title		= {Some methods of speeding up the convergence of iteration
		  methods},
  author	= {Polyak, Boris T},
  journal	= {USSR Computational Mathematics and Mathematical Physics},
  volume	= {4},
  number	= {5},
  pages		= {1--17},
  year		= {1964},
  publisher	= {Elsevier}
}

@InCollection{	  Prechelt.1998,
  title		= {Early stopping-but when?},
  author	= {Prechelt, Lutz},
  booktitle	= {Neural Networks: Tricks of the trade},
  pages		= {55--69},
  year		= {1998},
  publisher	= {Springer}
}

@Article{	  Quadrana.Cremonesi.Jannach.2018,
  title		= {Sequence-aware recommender systems},
  author	= {Quadrana, Massimo and Cremonesi, Paolo and Jannach,
		  Dietmar},
  journal	= {ACM Computing Surveys (CSUR)},
  volume	= {51},
  number	= {4},
  pages		= {66},
  year		= {2018},
  publisher	= {ACM}
}

@Misc{		  Quinlan.1993,
  title		= {C4. 5: programs for machine learning},
  author	= {Quinlan, J Ross},
  year		= {1993},
  publisher	= {Morgan Kaufmann Publishers Inc.}
}

@Article{	  Radford.Metz.Chintala.2015,
  title		= {Unsupervised representation learning with deep
		  convolutional generative adversarial networks},
  author	= {Radford, Alec and Metz, Luke and Chintala, Soumith},
  journal	= {arXiv preprint arXiv:1511.06434},
  year		= {2015}
}

@Article{	  Radford.Narasimhan.Salimans.ea.2018,
  title		= {Improving language understanding by generative
		  pre-training},
  author	= {Radford, Alec and Narasimhan, Karthik and Salimans, Tim
		  and Sutskever, Ilya},
  journal	= {OpenAI},
  year		= {2018}
}

@Article{	  Radford.Wu.Child.ea.2019,
  title		= {Language models are unsupervised multitask learners},
  author	= {Radford, Alec and Wu, Jeffrey and Child, Rewon and Luan,
		  David and Amodei, Dario and Sutskever, Ilya},
  journal	= {OpenAI Blog},
  volume	= {1},
  number	= {8},
  pages		= {9},
  year		= {2019}
}

@Article{	  Radhakrishna-Rao.1945,
  title		= {Information and accuracy attainable in the estimation of
		  statistical parameters},
  author	= {Radhakrishna Rao, C},
  journal	= {Bulletin of the Calcutta Mathematical Society},
  volume	= {37},
  number	= {3},
  pages		= {81--91},
  year		= {1945},
  publisher	= {Calcutta Mathematical Society}
}

@InProceedings{	  Radosavovic.Kosaraju.Girshick.ea.2020,
  title		= {Designing network design spaces},
  author	= {Radosavovic, Ilija and Kosaraju, Raj Prateek and Girshick,
		  Ross and He, Kaiming and Doll{\'a}r, Piotr},
  booktitle	= {Proceedings of the IEEE/CVF Conference on Computer Vision
		  and Pattern Recognition},
  pages		= {10428--10436},
  year		= {2020}
}

@Article{	  Rajpurkar.Zhang.Lopyrev.ea.2016,
  title		= {Squad: 100,000+ questions for machine comprehension of
		  text},
  author	= {Rajpurkar, Pranav and Zhang, Jian and Lopyrev, Konstantin
		  and Liang, Percy},
  journal	= {arXiv preprint arXiv:1606.05250},
  year		= {2016}
}

@Article{	  Ramachandran.Zoph.Le.2017,
  title		= {Searching for activation functions},
  author	= {Ramachandran, Prajit and Zoph, Barret and Le, Quoc V},
  journal	= {arXiv preprint arXiv:1710.05941},
  year		= {2017}
}

@InProceedings{	  Ranzato.Boureau.Chopra.ea.2007,
  title		= {A unified energy-based framework for unsupervised
		  learning},
  author	= {Ranzato, Marc’Aurelio and Boureau, Y-Lan and Chopra,
		  Sumit and LeCun, Yann},
  booktitle	= {Artificial Intelligence and Statistics},
  pages		= {371--379},
  year		= {2007},
  organization	= {PMLR}
}

@Article{	  Reddi.Kale.Kumar.2019,
  title		= {On the convergence of Adam and beyond},
  author	= {Reddi, Sashank J and Kale, Satyen and Kumar, Sanjiv},
  journal	= {arXiv preprint arXiv:1904.09237},
  year		= {2019}
}

@InProceedings{	  Redmon.Divvala.Girshick.ea.2016,
  title		= {You only look once: Unified, real-time object detection},
  author	= {Redmon, Joseph and Divvala, Santosh and Girshick, Ross and
		  Farhadi, Ali},
  booktitle	= {Proceedings of the IEEE conference on computer vision and
		  pattern recognition},
  pages		= {779--788},
  year		= {2016}
}

@Article{	  Redmon.Farhadi.2018,
  title		= {Yolov3: An incremental improvement},
  author	= {Redmon, Joseph and Farhadi, Ali},
  journal	= {arXiv preprint arXiv:1804.02767},
  year		= {2018}
}

@Article{	  Reed.De-Freitas.2015,
  title		= {Neural programmer-interpreters},
  author	= {Reed, Scott and De Freitas, Nando},
  journal	= {arXiv preprint arXiv:1511.06279},
  year		= {2015}
}

@InProceedings{	  Ren.He.Girshick.ea.2015,
  title		= {Faster r-cnn: Towards real-time object detection with
		  region proposal networks},
  author	= {Ren, Shaoqing and He, Kaiming and Girshick, Ross and Sun,
		  Jian},
  booktitle	= {Advances in neural information processing systems},
  pages		= {91--99},
  year		= {2015}
}

@InProceedings{	  Rendle.2010,
  title		= {Factorization machines},
  author	= {Rendle, Steffen},
  booktitle	= {2010 IEEE International Conference on Data Mining},
  pages		= {995--1000},
  year		= {2010},
  organization	= {IEEE}
}

@InProceedings{	  Rendle.Freudenthaler.Gantner.ea.2009,
  title		= {BPR: Bayesian personalized ranking from implicit
		  feedback},
  author	= {Rendle, Steffen and Freudenthaler, Christoph and Gantner,
		  Zeno and Schmidt-Thieme, Lars},
  booktitle	= {Proceedings of the twenty-fifth conference on uncertainty
		  in artificial intelligence},
  pages		= {452--461},
  year		= {2009},
  organization	= {AUAI Press}
}

@Article{	  Revels.Lubin.Papamarkou.2016,
  title		= {Forward-mode automatic differentiation in Julia},
  author	= {Revels, Jarrett and Lubin, Miles and Papamarkou,
		  Theodore},
  journal	= {arXiv preprint arXiv:1607.07892},
  year		= {2016}
}

@Article{	  Riesenhuber.Poggio.1999,
  title		= {Hierarchical models of object recognition in cortex},
  author	= {Riesenhuber, Maximilian and Poggio, Tomaso},
  journal	= {Nature neuroscience},
  volume	= {2},
  number	= {11},
  pages		= {1019--1025},
  year		= {1999},
  publisher	= {Nature Publishing Group}
}

@Book{		  Rockafellar.1970,
  address	= {Princeton, NJ},
  author	= {R.~T.~Rockafellar},
  publisher	= {Princeton University Press},
  series	= {Princeton Mathematics Series},
  title		= {Convex Analysis},
  volume	= 28,
  year		= 1970
}

@article{Rolnick.Veit.Belongie.Shavit.2017,
  title={Deep learning is robust to massive label noise},
  author={Rolnick, David and Veit, Andreas and Belongie, Serge and Shavit, Nir},
  journal={arXiv preprint arXiv:1705.10694},
  year={2017}
}


@Article{	  Rosenbaum.Rubin.1983,
  title		= {The central role of the propensity score in observational
		  studies for causal effects},
  author	= {Rosenbaum, Paul R and Rubin, Donald B},
  journal	= {Biometrika},
  volume	= {70},
  number	= {1},
  pages		= {41--55},
  year		= {1983},
  publisher	= {Oxford University Press}
}

@Book{		  Rudin.1973,
  address	= {New York},
  author	= {W.~Rudin},
  publisher	= {McGraw-Hill},
  title		= {Functional Analysis},
  year		= 1973
}

@Article{	  Rumelhart.Hinton.Williams.ea.1988,
  title		= {Learning representations by back-propagating errors},
  author	= {Rumelhart, David E and Hinton, Geoffrey E and Williams,
		  Ronald J and others},
  journal	= {Cognitive modeling},
  volume	= {5},
  number	= {3},
  pages		= {1},
  year		= {1988}
}

@InProceedings{	  Russakovsky.Deng.Huang.ea.2013,
  author	= "Olga Russakovsky and Jia Deng and Zhiheng Huang and
		  Alexander C. Berg and Li Fei-Fei",
  title		= "Detecting avocados to zucchinis: what have we done, and
		  where are we going?",
  booktitle	= "International Conference on Computer Vision (ICCV)",
  year		= "2013"
}

@Book{		  Russell.Norvig.2016,
  title		= {Artificial intelligence: a modern approach},
  author	= {Russell, Stuart J and Norvig, Peter},
  year		= {2016},
  publisher	= {Malaysia; Pearson Education Limited,}
}

@Article{	  Salton.Wong.Yang.1975,
  title		= {A vector space model for automatic indexing},
  author	= {Salton, Gerard and Wong, Anita and Yang, Chung-Shu},
  journal	= {Communications of the ACM},
  volume	= {18},
  number	= {11},
  pages		= {613--620},
  year		= {1975},
  publisher	= {ACM}
}

@InProceedings{	  Santurkar.Tsipras.Ilyas.ea.2018,
  title		= {How does batch normalization help optimization?},
  author	= {Santurkar, Shibani and Tsipras, Dimitris and Ilyas, Andrew
		  and Madry, Aleksander},
  booktitle	= {Advances in Neural Information Processing Systems},
  pages		= {2483--2493},
  year		= {2018}
}

@Article{	  Sarwar.Karypis.Konstan.ea.2001,
  title		= {Item-based collaborative filtering recommendation
		  algorithms.},
  author	= {Sarwar, Badrul Munir and Karypis, George and Konstan,
		  Joseph A and Riedl, John and others},
  journal	= {Www},
  volume	= {1},
  pages		= {285--295},
  year		= {2001}
}

@InProceedings{	  Schein.Popescul.Ungar.ea.2002,
  title		= {Methods and metrics for cold-start recommendations},
  author	= {Schein, Andrew I and Popescul, Alexandrin and Ungar, Lyle
		  H and Pennock, David M},
  booktitle	= {Proceedings of the 25th annual international ACM SIGIR
		  conference on Research and development in information
		  retrieval},
  pages		= {253--260},
  year		= {2002},
  organization	= {ACM}
}

@InProceedings{	  Scholkopf.Burges.Vapnik.1996,
  title		= {Incorporating invariances in support vector learning
		  machines},
  author	= {Sch{\"o}lkopf, Bernhard and Burges, Chris and Vapnik,
		  Vladimir},
  booktitle	= {International Conference on Artificial Neural Networks},
  pages		= {47--52},
  year		= {1996},
  organization	= {Springer}
}

@InProceedings{	  Scholkopf.Herbrich.Smola.2001,
  address	= {London, UK},
  author	= {B.~Sch{\"o}lkopf and R.~Herbrich and A. J. Smola},
  booktitle	= {Proc.\ Annual Conf.\ Computational Learning Theory},
  editor	= {D.~P.~Helmbold and B.~Williamson},
  number	= 2111,
  pages		= {416-426},
  publisher	= {Springer-Verlag},
  series	= {Lecture Notes in Comput. Sci.},
  title		= {A Generalized Representer Theorem},
  year		= 2001
}

@Book{		  Scholkopf.Smola.2002,
  title		= {Learning with kernels: support vector machines,
		  regularization, optimization, and beyond},
  author	= {Sch{\"o}lkopf, Bernhard and Smola, Alexander J},
  year		= {2002},
  publisher	= {Adaptive Computation and Machine Learning Series}
}

@Article{	  Schuster.Paliwal.1997,
  title		= {Bidirectional recurrent neural networks},
  author	= {Schuster, Mike and Paliwal, Kuldip K},
  journal	= {IEEE Transactions on Signal Processing},
  volume	= {45},
  number	= {11},
  pages		= {2673--2681},
  year		= {1997},
  publisher	= {IEEE}
}

@InProceedings{	  Sedhain.Menon.Sanner.ea.2015,
  title		= {Autorec: Autoencoders meet collaborative filtering},
  author	= {Sedhain, Suvash and Menon, Aditya Krishna and Sanner,
		  Scott and Xie, Lexing},
  booktitle	= {Proceedings of the 24th International Conference on World
		  Wide Web},
  pages		= {111--112},
  year		= {2015},
  organization	= {ACM}
}

@Article{	  Sennrich.Haddow.Birch.2015,
  title		= {Neural machine translation of rare words with subword
		  units},
  author	= {Sennrich, Rico and Haddow, Barry and Birch, Alexandra},
  journal	= {arXiv preprint arXiv:1508.07909},
  year		= {2015}
}

@Article{	  Sergeev.Del-Balso.2018,
  title		= {Horovod: fast and easy distributed deep learning in
		  TensorFlow},
  author	= {Sergeev, Alexander and Del Balso, Mike},
  journal	= {arXiv preprint arXiv:1802.05799},
  year		= {2018}
}

@Article{	  Shannon.1948,
  author	= {Shannon, Claude Elwood},
  journal	= {The Bell System Technical Journal},
  month		= {7},
  number	= 3,
  pages		= {379--423},
  publisher	= {Nokia Bell Labs},
  title		= {A Mathematical Theory of Communication},
  volume	= 27,
  year		= 1948
}

@InProceedings{	  Shao.Yao.Sun.ea.2020,
  title		= {ControlVAE: Controllable Variational Autoencoder},
  author	= {Shao, Huajie and Yao, Shuochao and Sun, Dachun and Zhang,
		  Aston and Liu, Shengzhong and Liu, Dongxin and Wang, Jun
		  and Abdelzaher, Tarek},
  booktitle	= {Proceedings of the 37th International Conference on
		  Machine Learning},
  year		= {2020},
  organization	= {JMLR. org}
}

@Article{	  Silver.Huang.Maddison.ea.2016,
  title		= {Mastering the game of Go with deep neural networks and
		  tree search},
  author	= {Silver, David and Huang, Aja and Maddison, Chris J and
		  Guez, Arthur and Sifre, Laurent and Van Den Driessche,
		  George and Schrittwieser, Julian and Antonoglou, Ioannis
		  and Panneershelvam, Veda and Lanctot, Marc and others},
  journal	= {nature},
  volume	= {529},
  number	= {7587},
  pages		= {484},
  year		= {2016},
  publisher	= {Nature Publishing Group}
}

@InCollection{	  Simard.LeCun.Denker.ea.1998,
  title		= {Transformation invariance in pattern recognition—tangent
		  distance and tangent propagation},
  author	= {Simard, Patrice Y and LeCun, Yann A and Denker, John S and
		  Victorri, Bernard},
  booktitle	= {Neural networks: tricks of the trade},
  pages		= {239--274},
  year		= {1998},
  publisher	= {Springer}
}

@Article{	  Simonyan.Zisserman.2014,
  title		= {Very deep convolutional networks for large-scale image
		  recognition},
  author	= {Simonyan, Karen and Zisserman, Andrew},
  journal	= {arXiv preprint arXiv:1409.1556},
  year		= {2014}
}

@InProceedings{	  Sivic.Zisserman.2003,
  title		= {Video Google: A text retrieval approach to object matching
		  in videos},
  author	= {Sivic, Josef and Zisserman, Andrew},
  booktitle	= {Computer Vision, IEEE International Conference on},
  volume	= {3},
  pages		= {1470--1470},
  year		= {2003},
  organization	= {IEEE Computer Society}
}

@Article{	  Smola.Narayanamurthy.2010,
  title		= {An architecture for parallel topic models},
  author	= {Smola, Alexander and Narayanamurthy, Shravan},
  journal	= {Proceedings of the VLDB Endowment},
  volume	= {3},
  number	= {1-2},
  pages		= {703--710},
  year		= {2010},
  publisher	= {VLDB Endowment}
}

@PhDThesis{	  Speelpenning.1980,
  title		= {Compiling fast partial derivatives of functions given by
		  algorithms},
  author	= {Speelpenning, Bert},
  year		= {1980},
  school	= {University of Illinois at Urbana-Champaign}
}

@Book{		  Spiegelhalter.2019,
  title		= {The art of statistics: Learning from data},
  author	= {Spiegelhalter, David},
  year		= {2019},
  publisher	= {Penguin UK}
}

@Article{	  Srivastava.Hinton.Krizhevsky.ea.2014,
  title		= {Dropout: a simple way to prevent neural networks from
		  overfitting},
  author	= {Srivastava, Nitish and Hinton, Geoffrey and Krizhevsky,
		  Alex and Sutskever, Ilya and Salakhutdinov, Ruslan},
  journal	= {The Journal of Machine Learning Research},
  volume	= {15},
  number	= {1},
  pages		= {1929--1958},
  year		= {2014},
  publisher	= {JMLR. org}
}

@Book{		  Strang.1993,
  title		= {Introduction to linear algebra},
  author	= {Strang, Gilbert},
  volume	= {3},
  year		= {1993},
  publisher	= {Wellesley-Cambridge Press Wellesley, MA}
}

@Article{	  Su.Khoshgoftaar.2009,
  title		= {A survey of collaborative filtering techniques},
  author	= {Su, Xiaoyuan and Khoshgoftaar, Taghi M},
  journal	= {Advances in artificial intelligence},
  volume	= {2009},
  year		= {2009},
  publisher	= {Hindawi}
}

@InProceedings{	  Sukhbaatar.Weston.Fergus.ea.2015,
  title		= {End-to-end memory networks},
  author	= {Sukhbaatar, Sainbayar and Weston, Jason and Fergus, Rob
		  and others},
  booktitle	= {Advances in neural information processing systems},
  pages		= {2440--2448},
  year		= {2015}
}

@InProceedings{	  Sutskever.Martens.Dahl.ea.2013,
  title		= {On the importance of initialization and momentum in deep
		  learning},
  author	= {Sutskever, Ilya and Martens, James and Dahl, George and
		  Hinton, Geoffrey},
  booktitle	= {International conference on machine learning},
  pages		= {1139--1147},
  year		= {2013}
}

@article{chan2015listen,
  title={Listen, attend and spell},
  author={Chan, William and Jaitly, Navdeep and Le, Quoc V and Vinyals, Oriol},
  journal={arXiv preprint arXiv:1508.01211},
  year={2015}
}

@article{RabJua93,
  title={Fundamentals of speech recognition},
  author={Rabiner, Lawrence and Juang, Biing-Hwang},
  year={1993},
  publisher={Prentice hall}
}

@article{yang2016neural,
  title={Neural machine translation with recurrent attention modeling},
  author={Yang, Zichao and Hu, Zhiting and Deng, Yuntian and Dyer, Chris and Smola, Alex},
  journal={arXiv preprint arXiv:1607.05108},
  year={2016}
}


@InProceedings{	  Sutskever.Vinyals.Le.2014,
  title		= {Sequence to sequence learning with neural networks},
  author	= {Sutskever, Ilya and Vinyals, Oriol and Le, Quoc V},
  booktitle	= {Advances in neural information processing systems},
  pages		= {3104--3112},
  year		= {2014}
}

@InProceedings{	  Szegedy.Ioffe.Vanhoucke.ea.2017,
  title		= {Inception-v4, inception-resnet and the impact of residual
		  connections on learning},
  author	= {Szegedy, Christian and Ioffe, Sergey and Vanhoucke,
		  Vincent and Alemi, Alexander A},
  booktitle	= {Thirty-First AAAI Conference on Artificial Intelligence},
  year		= {2017}
}

@InProceedings{	  Szegedy.Liu.Jia.ea.2015,
  title		= {Going deeper with convolutions},
  author	= {Szegedy, Christian and Liu, Wei and Jia, Yangqing and
		  Sermanet, Pierre and Reed, Scott and Anguelov, Dragomir and
		  Erhan, Dumitru and Vanhoucke, Vincent and Rabinovich,
		  Andrew},
  booktitle	= {Proceedings of the IEEE conference on computer vision and
		  pattern recognition},
  pages		= {1--9},
  year		= {2015}
}

@InProceedings{	  Szegedy.Vanhoucke.Ioffe.ea.2016,
  title		= {Rethinking the inception architecture for computer
		  vision},
  author	= {Szegedy, Christian and Vanhoucke, Vincent and Ioffe,
		  Sergey and Shlens, Jon and Wojna, Zbigniew},
  booktitle	= {Proceedings of the IEEE conference on computer vision and
		  pattern recognition},
  pages		= {2818--2826},
  year		= {2016}
}

@Article{	  Tallec.Ollivier.2017,
  title		= {Unbiasing truncated backpropagation through time},
  author	= {Tallec, Corentin and Ollivier, Yann},
  journal	= {arXiv preprint arXiv:1705.08209},
  year		= {2017}
}

@InProceedings{	  Tang.Wang.2018,
  title		= {Personalized top-n sequential recommendation via
		  convolutional sequence embedding},
  author	= {Tang, Jiaxi and Wang, Ke},
  booktitle	= {Proceedings of the Eleventh ACM International Conference
		  on Web Search and Data Mining},
  pages		= {565--573},
  year		= {2018},
  organization	= {ACM}
}

@Article{	  Taskar.Guestrin.Koller.2004,
  title		= {Max-margin Markov networks},
  author	= {Taskar, Ben and Guestrin, Carlos and Koller, Daphne},
  journal	= {Advances in neural information processing systems},
  volume	= {16},
  pages		= {25},
  year		= {2004}
}

@Article{	  Tay.Dehghani.Bahri.ea.2020,
  title		= {Efficient transformers: A survey},
  author	= {Tay, Yi and Dehghani, Mostafa and Bahri, Dara and Metzler,
		  Donald},
  journal	= {arXiv preprint arXiv:2009.06732},
  year		= {2020}
}

@Article{	  Teye.Azizpour.Smith.2018,
  title		= {Bayesian uncertainty estimation for batch normalized deep
		  networks},
  author	= {Teye, Mattias and Azizpour, Hossein and Smith, Kevin},
  journal	= {arXiv preprint arXiv:1802.06455},
  year		= {2018}
}

@Article{	  Thomee.Shamma.Friedland.ea.2016,
  title		= {YFCC100M: The new data in multimedia research},
  author	= {Thomee, Bart and Shamma, David A and Friedland, Gerald and
		  Elizalde, Benjamin and Ni, Karl and Poland, Douglas and
		  Borth, Damian and Li, Li-Jia},
  journal	= {Communications of the ACM},
  volume	= {59},
  number	= {2},
  pages		= {64--73},
  year		= {2016},
  publisher	= {ACM New York, NY, USA}
}

@Book{		  Thompson.2015,
  title		= {Mathematical statistical mechanics},
  author	= {Thompson, Colin J},
  year		= {2015},
  publisher	= {Princeton University Press}
}

@Article{	  Tieleman.Hinton.2012,
  title		= {Lecture 6.5-rmsprop: Divide the gradient by a running
		  average of its recent magnitude},
  author	= {Tieleman, Tijmen and Hinton, Geoffrey},
  journal	= {COURSERA: Neural networks for machine learning},
  volume	= {4},
  number	= {2},
  pages		= {26--31},
  year		= {2012}
}

@Article{	  Torralba.Fergus.Freeman.2008,
  title		= {80 million tiny images: A large data set for nonparametric
		  object and scene recognition},
  author	= {Torralba, Antonio and Fergus, Rob and Freeman, William T},
  journal	= {IEEE transactions on pattern analysis and machine
		  intelligence},
  volume	= {30},
  number	= {11},
  pages		= {1958--1970},
  year		= {2008},
  publisher	= {IEEE}
}

@Article{	  Toscher.Jahrer.Bell.2009,
  title		= {The bigchaos solution to the netflix grand prize},
  author	= {T{\"o}scher, Andreas and Jahrer, Michael and Bell, Robert
		  M},
  journal	= {Netflix prize documentation},
  pages		= {1--52},
  year		= {2009}
}

@Article{	  Treisman.Gelade.1980,
  title		= {A feature-integration theory of attention},
  author	= {Treisman, Anne M and Gelade, Garry},
  journal	= {Cognitive psychology},
  volume	= {12},
  number	= {1},
  pages		= {97--136},
  year		= {1980},
  publisher	= {Elsevier}
}

@Article{	  Tsoumakas.Katakis.2007,
  title		= {Multi-label classification: An overview},
  author	= {Tsoumakas, Grigorios and Katakis, Ioannis},
  journal	= {International Journal of Data Warehousing and Mining
		  (IJDWM)},
  volume	= {3},
  number	= {3},
  pages		= {1--13},
  year		= {2007},
  publisher	= {IGI Global}
}

@Article{	  Turing.1950,
  title		= {Computing machinery and intelligence},
  author	= {Turing, Alan},
  journal	= {Mind},
  volume	= {59},
  number	= {236},
  pages		= {433},
  year		= {1950}
}

@Article{	  Uijlings.Van-De-Sande.Gevers.ea.2013,
  title		= {Selective search for object recognition},
  author	= {Uijlings, Jasper RR and Van De Sande, Koen EA and Gevers,
		  Theo and Smeulders, Arnold WM},
  journal	= {International journal of computer vision},
  volume	= {104},
  number	= {2},
  pages		= {154--171},
  year		= {2013},
  publisher	= {Springer}
}

@Book{		  Van-Loan.Golub.1983,
  title		= {Matrix computations},
  author	= {Van Loan, Charles F and Golub, Gene H},
  year		= {1983},
  publisher	= {Johns Hopkins University Press}
}

@InProceedings{	  Vapnik.1992,
  title		= {Principles of risk minimization for learning theory},
  author	= {Vapnik, Vladimir},
  booktitle	= {Advances in neural information processing systems},
  pages		= {831--838},
  year		= {1992}
}

@Book{		  Vapnik.1998,
  address	= {New York},
  author	= {V. Vapnik},
  publisher	= {John Wiley and Sons},
  title		= {Statistical Learning Theory},
  year		= 1998
}

@Article{	  Vapnik.Chervonenkis.1964,
  author	= {V. Vapnik and A. Chervonenkis},
  issue		= 1,
  journal	= {Automation and Remote Control},
  title		= {A note on one class of perceptrons},
  volume	= 25,
  year		= 1964
}

@Article{	  Vapnik.Chervonenkis.1968,
  author	= {V. Vapnik and A. Chervonenkis},
  journal	= {Dokl.\ Akad.\ Nauk SSSR},
  pages		= {915-918},
  title		= {Uniform convergence of frequencies of occurence of events
		  to their probabilities},
  volume	= 181,
  year		= 1968
}

@Article{	  Vapnik.Chervonenkis.1971,
  author	= {V. Vapnik and A. Chervonenkis},
  journal	= {Theory Probab. Appl.},
  number	= 2,
  pages		= {264-281},
  title		= {On the uniform convergence of relative frequencies of
		  events to their probabilities},
  volume	= 16,
  year		= 1971
}

@Book{		  Vapnik.Chervonenkis.1974,
  address	= {Moscow},
  author	= {V. Vapnik and A. Chervonenkis},
  note		= {(German Translation: W. Wapnik \& A. Tscherwonenkis, {\em
		  Theorie der Zeichenerkennung}, Akademie-Verlag, Berlin,
		  1979)},
  publisher	= {Nauka},
  title		= {Theory of Pattern Recognition [in Russian]},
  year		= 1974
}

@Article{	  Vapnik.Chervonenkis.1974*1,
  author	= {V.~N. Vapnik and A.~Y. Chervonenkis},
  journal	= {Automation and Remote Control},
  pages		= {1226--1235, 1403--1412},
  title		= {Ordered risk minimization},
  volume	= 35,
  year		= 1974
}

@Book{		  Vapnik.Chervonenkis.1974*2,
  address	= {Moscow: Nauka},
  author	= {V. Vapnik and A. Chervonenkis},
  title		= {Teoriya raspoznavaniya obrazov: Statisticheskie problemy
		  obucheniya. (Russian) [Theory of pattern recognition:
		  Statistical problems of learning]},
  year		= 1974
}

@Article{	  Vapnik.Chervonenkis.1981,
  author	= {V. Vapnik and A. Chervonenkis},
  journal	= {Teoriya Veroyatnostei i Ee Primeneniya},
  number	= 3,
  pages		= {543-564},
  title		= {The necessary and sufficient conditions for the uniform
		  convergence of averages to their expected values},
  volume	= 26,
  year		= 1981
}

@Article{	  Vapnik.Chervonenkis.1991,
  author	= {V. Vapnik and A. Chervonenkis},
  journal	= {Pattern Recognition and Image Analysis},
  number	= 3,
  pages		= {283-305},
  title		= {The necessary and sufficient conditions for consistency in
		  the empirical risk minimization method},
  volume	= 1,
  year		= 1991
}

@Article{	  Vapnik.Levin.Le-Cun.1994,
  title		= {Measuring the VC-dimension of a learning machine},
  author	= {Vapnik, Vladimir and Levin, Esther and Le Cun, Yann},
  journal	= {Neural computation},
  volume	= {6},
  number	= {5},
  pages		= {851--876},
  year		= {1994},
  publisher	= {MIT Press}
}

@InProceedings{	  Vaswani.Shazeer.Parmar.ea.2017,
  title		= {Attention is all you need},
  author	= {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and
		  Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and
		  Kaiser, {\L}ukasz and Polosukhin, Illia},
  booktitle	= {Advances in neural information processing systems},
  pages		= {5998--6008},
  year		= {2017}
}

@Book{		  Wahba.1990,
  title		= {Spline models for observational data},
  author	= {Wahba, Grace},
  year		= {1990},
  publisher	= {SIAM}
}

@Article{	  Waibel.Hanazawa.Hinton.ea.1989,
  title		= {Phoneme recognition using time-delay neural networks},
  author	= {Waibel, Alex and Hanazawa, Toshiyuki and Hinton, Geoffrey
		  and Shikano, Kiyohiro and Lang, Kevin J},
  journal	= {IEEE transactions on acoustics, speech, and signal
		  processing},
  volume	= {37},
  number	= {3},
  pages		= {328--339},
  year		= {1989},
  publisher	= {IEEE}
}

@InProceedings{	  Wang.Davidson.Pan.ea.2016,
  title		= {Gunrock: A high-performance graph processing library on
		  the GPU},
  author	= {Wang, Yangzihao and Davidson, Andrew and Pan, Yuechao and
		  Wu, Yuduo and Riffel, Andy and Owens, John D},
  booktitle	= {ACM SIGPLAN Notices},
  volume	= {51},
  number	= {8},
  pages		= {11},
  year		= {2016},
  organization	= {ACM}
}

@Article{	  Wang.Li.Liberty.ea.2018,
  title		= {Optimal Message Scheduling for Aggregation},
  author	= {Wang, Leyuan and Li, Mu and Liberty, Edo and Smola, Alex
		  J},
  journal	= {NETWORKS},
  volume	= {2},
  number	= {3},
  pages		= {2--3},
  year		= {2018}
}

@Article{	  Warstadt.Singh.Bowman.2019,
  title		= {Neural network acceptability judgments},
  author	= {Warstadt, Alex and Singh, Amanpreet and Bowman, Samuel R},
  journal	= {Transactions of the Association for Computational
		  Linguistics},
  volume	= {7},
  pages		= {625--641},
  year		= {2019},
  publisher	= {MIT Press}
}

@Book{		  Wasserman.2013,
  title		= {All of statistics: a concise course in statistical
		  inference},
  author	= {Wasserman, Larry},
  year		= {2013},
  publisher	= {Springer Science \& Business Media}
}

@Article{	  Watkins.Dayan.1992,
  title		= {Q-learning},
  author	= {Watkins, Christopher JCH and Dayan, Peter},
  journal	= {Machine learning},
  volume	= {8},
  number	= {3-4},
  pages		= {279--292},
  year		= {1992},
  publisher	= {Springer}
}

@Article{	  Watson.1964,
  title		= {Smooth regression analysis},
  author	= {Watson, Geoffrey S},
  journal	= {Sankhy{\=a}: The Indian Journal of Statistics, Series A},
  pages		= {359--372},
  year		= {1964},
  publisher	= {JSTOR}
}

@InProceedings{	  Welling.Teh.2011,
  title		= {Bayesian learning via stochastic gradient Langevin
		  dynamics},
  author	= {Welling, Max and Teh, Yee W},
  booktitle	= {Proceedings of the 28th international conference on
		  machine learning (ICML-11)},
  pages		= {681--688},
  year		= {2011}
}

@Article{	  Wengert.1964,
  title		= {A simple automatic derivative evaluation program},
  author	= {Wengert, Robert Edwin},
  journal	= {Communications of the ACM},
  volume	= {7},
  number	= {8},
  pages		= {463--464},
  year		= {1964},
  publisher	= {ACM New York, NY, USA}
}

@Article{	  Werbos.1990,
  title		= {Backpropagation through time: what it does and how to do
		  it},
  author	= {Werbos, Paul J},
  journal	= {Proceedings of the IEEE},
  volume	= {78},
  number	= {10},
  pages		= {1550--1560},
  year		= {1990},
  publisher	= {IEEE}
}

@InProceedings{	  Wigner.1958,
  title		= {On the distribution of the roots of certain symmetric
		  matrices},
  author	= {Wigner, Eugene P.},
  booktitle	= {Ann. Math},
  pages		= {325--327},
  year		= {1958}
}

@TechReport{	  Williams.Waterman.Patterson.2009,
  title		= {Roofline: An insightful visual performance model for
		  floating-point programs and multicore architectures},
  author	= {Williams, Samuel and Waterman, Andrew and Patterson,
		  David},
  year		= {2009},
  institution	= {Lawrence Berkeley National Lab.(LBNL), Berkeley, CA
		  (United States)}
}

@Article{	  Wood.Gasthaus.Archambeau.ea.2011,
  title		= {The sequence memoizer},
  author	= {Wood, Frank and Gasthaus, Jan and Archambeau, C{\'e}dric
		  and James, Lancelot and Teh, Yee Whye},
  journal	= {Communications of the ACM},
  volume	= {54},
  number	= {2},
  pages		= {91--98},
  year		= {2011},
  publisher	= {ACM}
}

@InProceedings{	  Wu.Ahmed.Beutel.ea.2017,
  title		= {Recurrent recommender networks},
  author	= {Wu, Chao-Yuan and Ahmed, Amr and Beutel, Alex and Smola,
		  Alexander J and Jing, How},
  booktitle	= {Proceedings of the tenth ACM international conference on
		  web search and data mining},
  pages		= {495--503},
  year		= {2017},
  organization	= {ACM}
}

@Article{	  Wu.Schuster.Chen.ea.2016,
  title		= {Google's neural machine translation system: Bridging the
		  gap between human and machine translation},
  author	= {Wu, Yonghui and Schuster, Mike and Chen, Zhifeng and Le,
		  Quoc V and Norouzi, Mohammad and Macherey, Wolfgang and
		  Krikun, Maxim and Cao, Yuan and Gao, Qin and Macherey,
		  Klaus and others},
  journal	= {arXiv preprint arXiv:1609.08144},
  year		= {2016}
}

@InProceedings{	  Xiao.Bahri.Sohl-Dickstein.ea.2018,
  title		= {Dynamical Isometry and a Mean Field Theory of CNNs: How to
		  Train 10,000-Layer Vanilla Convolutional Neural Networks},
  author	= {Xiao, Lechao and Bahri, Yasaman and Sohl-Dickstein, Jascha
		  and Schoenholz, Samuel and Pennington, Jeffrey},
  booktitle	= {International Conference on Machine Learning},
  pages		= {5393--5402},
  year		= {2018}
}

@Article{	  Xiao.Rasul.Vollgraf.2017,
  title		= {Fashion-mnist: a novel image dataset for benchmarking
		  machine learning algorithms},
  author	= {Xiao, Han and Rasul, Kashif and Vollgraf, Roland},
  journal	= {arXiv preprint arXiv:1708.07747},
  year		= {2017}
}

@InProceedings{	  Xie.Girshick.Dollar.ea.2017,
  title		= {Aggregated residual transformations for deep neural
		  networks},
  author	= {Xie, Saining and Girshick, Ross and Doll{\'a}r, Piotr and
		  Tu, Zhuowen and He, Kaiming},
  booktitle	= {Proceedings of the IEEE conference on computer vision and
		  pattern recognition},
  pages		= {1492--1500},
  year		= {2017}
}

@InProceedings{	  Xiong.Wu.Alleva.ea.2018,
  title		= {The Microsoft 2017 conversational speech recognition
		  system},
  author	= {Xiong, Wayne and Wu, Lingfeng and Alleva, Fil and Droppo,
		  Jasha and Huang, Xuedong and Stolcke, Andreas},
  booktitle	= {2018 IEEE International Conference on Acoustics, Speech
		  and Signal Processing (ICASSP)},
  pages		= {5934--5938},
  year		= {2018},
  organization	= {IEEE}
}

@InProceedings{	  Yamaguchi.Sakamoto.Akabane.ea.1990,
  title		= {A neural network for speaker-independent isolated word
		  recognition},
  author	= {Yamaguchi, Kouichi and Sakamoto, Kenji and Akabane, Toshio
		  and Fujimoto, Yoshiji},
  booktitle	= {First International Conference on Spoken Language
		  Processing},
  year		= {1990}
}

@InProceedings{	  Yang.Moczulski.Denil.ea.2015,
  title		= {Deep fried convnets},
  author	= {Yang, Zichao and Moczulski, Marcin and Denil, Misha and De
		  Freitas, Nando and Smola, Alex and Song, Le and Wang,
		  Ziyu},
  booktitle	= {Proceedings of the IEEE International Conference on
		  Computer Vision},
  pages		= {1476--1483},
  year		= {2015}
}

@InProceedings{	  Ye.Yin.Lee.ea.2011,
  title		= {Exploiting geographical influence for collaborative
		  point-of-interest recommendation},
  author	= {Ye, Mao and Yin, Peifeng and Lee, Wang-Chien and Lee,
		  Dik-Lun},
  booktitle	= {Proceedings of the 34th international ACM SIGIR conference
		  on Research and development in Information Retrieval},
  pages		= {325--334},
  year		= {2011},
  organization	= {ACM}
}

@Article{	  You.Gitman.Ginsburg.2017,
  title		= {Large batch training of convolutional networks},
  author	= {You, Yang and Gitman, Igor and Ginsburg, Boris},
  journal	= {arXiv preprint arXiv:1708.03888},
  year		= {2017}
}

@Article{	  Yu.1994,
  title		= {Rates of convergence for empirical processes of stationary
		  mixing sequences},
  author	= {Yu, Bin},
  journal	= {The Annals of Probability},
  pages		= {94--116},
  year		= {1994},
  publisher	= {JSTOR}
}

@InProceedings{	  Zaheer.Reddi.Sachan.ea.2018,
  title		= {Adaptive methods for nonconvex optimization},
  author	= {Zaheer, Manzil and Reddi, Sashank and Sachan, Devendra and
		  Kale, Satyen and Kumar, Sanjiv},
  booktitle	= {Advances in Neural Information Processing Systems},
  pages		= {9793--9803},
  year		= {2018}
}

@Article{	  Zeiler.2012,
  title		= {ADADELTA: an adaptive learning rate method},
  author	= {Zeiler, Matthew D},
  journal	= {arXiv preprint arXiv:1212.5701},
  year		= {2012}
}

@Article{	  Zeiler.Fergus.2013,
  title		= {Stochastic pooling for regularization of deep
		  convolutional neural networks},
  author	= {Zeiler, Matthew D and Fergus, Rob},
  journal	= {arXiv preprint arXiv:1301.3557},
  year		= {2013}
}

@Article{	  Zhang.2004,
  title		= {Statistical behavior and consistency of classification
		  methods based on convex risk minimization},
  author	= {Zhang, Tong},
  journal	= {The Annals of Statistics},
  volume	= {32},
  number	= {1},
  pages		= {56--85},
  year		= {2004},
  publisher	= {Institute of Mathematical Statistics}
}

@Article{	  Zhang.Sun.Jiang.ea.2021,
  title		= {ByteTrack: Multi-Object Tracking by Associating Every
		  Detection Box},
  author	= {Yifu Zhang and Peize Sun and Yi Jiang and Dongdong Yu and
		  Zehuan Yuan and Ping Luo and Wenyu Liu and Xinggang Wang},
  journal	= {arXiv preprint arXiv:2110.06864},
  year		= {2021}
}

@InProceedings{	  Zhang.Tay.Zhang.ea.2021,
  title		= {Beyond Fully-Connected Layers with Quaternions:
		  Parameterization of Hypercomplex Multiplications with 1/n
		  Parameters},
  author	= {Zhang, Aston and Tay, Yi and Zhang, Shuai and Chan, Alvin
		  and Luu, Anh Tuan and Hui, Siu Cheung and Fu, Jie},
  booktitle	= {International Conference on Learning Representations},
  year		= {2021}
}

@Article{	  Zhang.Yao.Sun.ea.2019,
  title		= {Deep learning based recommender system: A survey and new
		  perspectives},
  author	= {Zhang, Shuai and Yao, Lina and Sun, Aixin and Tay, Yi},
  journal	= {ACM Computing Surveys (CSUR)},
  volume	= {52},
  number	= {1},
  pages		= {5},
  year		= {2019},
  publisher	= {ACM}
}

@InProceedings{	  Zhang.ea.1988,
  title		= {Shift-invariant pattern recognition neural network and its
		  optical architecture},
  author	= {Zhang, Wei and others},
  booktitle	= {Proceedings of annual conference of the Japan Society of
		  Applied Physics},
  year		= {1988}
}

@Article{	  Zhao.Zheng.Xu.ea.2019,
  title		= {Object detection with deep learning: A review},
  author	= {Zhao, Zhong-Qiu and Zheng, Peng and Xu, Shou-tao and Wu,
		  Xindong},
  journal	= {IEEE transactions on neural networks and learning
		  systems},
  volume	= {30},
  number	= {11},
  pages		= {3212--3232},
  year		= {2019},
  publisher	= {IEEE}
}

@InProceedings{	  Zhu.Kiros.Zemel.ea.2015,
  title		= {Aligning books and movies: Towards story-like visual
		  explanations by watching movies and reading books},
  author	= {Zhu, Yukun and Kiros, Ryan and Zemel, Rich and
		  Salakhutdinov, Ruslan and Urtasun, Raquel and Torralba,
		  Antonio and Fidler, Sanja},
  booktitle	= {Proceedings of the IEEE international conference on
		  computer vision},
  pages		= {19--27},
  year		= {2015}
}

@InProceedings{	  Zhu.Park.Isola.ea.2017,
  title		= {Unpaired image-to-image translation using cycle-consistent
		  adversarial networks},
  author	= {Zhu, Jun-Yan and Park, Taesung and Isola, Phillip and
		  Efros, Alexei A},
  booktitle	= {Proceedings of the IEEE international conference on
		  computer vision},
  pages		= {2223--2232},
  year		= {2017}
}

@article{naor1999construction,
  title={On the Construction of Pseudorandom Permutations: Luby—Rackoff Revisited},
  author={Naor, Moni and Reingold, Omer},
  journal={Journal of Cryptology},
  volume={12},
  number={1},
  pages={29--66},
  year={1999},
  publisher={Springer}
}

@article{griewank1989automatic,
  title={On automatic differentiation},
  author={Griewank, Andreas},
  journal={Mathematical Programming: recent developments and applications},
  volume={6},
  number={6},
  pages={83--107},
  year={1989},
  publisher={Citeseer}
}

@article{black1973pricing,
  title={The Pricing of Options and Corporate Liabilities},
  author={Black, Fischer and Scholes, Myron},
  journal={The Journal of Political Economy},
  pages={637--654},
  year={1973},
  publisher={JSTOR}
}

@article{wengert1964simple,
  title={A simple automatic derivative evaluation program},
  author={Wengert, Robert Edwin},
  journal={Communications of the ACM},
  volume={7},
  number={8},
  pages={463--464},
  year={1964},
  publisher={ACM New York, NY, USA}
}

@article{revels2016forward,
  title={Forward-mode automatic differentiation in Julia},
  author={Revels, Jarrett and Lubin, Miles and Papamarkou, Theodore},
  journal={arXiv preprint arXiv:1607.07892},
  year={2016}
}

@article{Mangasarian65,
  Author =	 {O.~L.~Mangasarian},
  Journal =	 {Oper. Res.},
  Pages =	 {444-452},
  Title =	 {Linear and Nonlinear Separation of Patterns by
                  Linear Programming},
  Volume =	 13,
  Year =	 1965
}

@book{Rockafellar70,
  Address =	 {Princeton, NJ},
  Author =	 {R.~T.~Rockafellar},
  Publisher =	 {Princeton University Press},
  Series =	 {Princeton Mathematics Series},
  Title =	 {Convex Analysis},
  Volume =	 28,
  Year =	 1970
}

@article{McCPit43,
  Author =	 {W.~S.~McCulloch and W.~H.~Pitts},
  Journal =	 {Bull.~Math.~Biophy},
  Pages =	 {115-133},
  Title =	 {A logical calculus of the idea immanent in nervous
                  activity},
  Volume =	 5,
  Year =	 1943
}

@inproceedings{kalman1992tanh,
  title={Why tanh: choosing a sigmoidal function},
  author={Kalman, Barry L and Kwasny, Stan C},
  booktitle={[Proceedings 1992] IJCNN International Joint Conference on Neural Networks},
  volume={4},
  pages={578--581},
  year={1992},
  organization={IEEE}
}

@article{lecun1998efficient,
  title={Efficient backprop},
  author={LeCun, Yann and Bottou, Leon and Orr, G and Muller, Klaus-Robert},
  journal={Neural Networks: Tricks of the Trade. New York: Springer},
  year={1998}
}

@article{mangram2013simplified,
  title={A simplified perspective of the Markowitz portfolio theory},
  author={Mangram, Myles E},
  journal={Global journal of business research},
  volume={7},
  number={1},
  pages={59--70},
  year={2013}
}

@book{legendre1805memoire,
  title={M{\'e}moire sur les op{\'e}rations trigonom{\'e}triques: dont les r{\'e}sultats d{\'e}pendent de la figure de la terre},
  author={Legendre, Adrien Marie},
  number={1},
  year={1805},
  publisher={F. Didot}
}

@article{gauss1809theoria,
  title={Theoria motus corporum coelestum},
  author={Gauss, Carl Friedrich},
  journal={Werke},
  year={1809}
}

@misc{golub1996matrix,
  title={Matrix computations. Johns Hopkins studies in the mathematical sciences},
  author={Golub, Gene H and Van Loan, Charles F},
  year={1996},
  publisher={Johns Hopkins University Press, Baltimore, MD,}
}

@article{liu1989limited,
  title={On the limited memory BFGS method for large scale optimization},
  author={Liu, Dong C and Nocedal, Jorge},
  journal={Mathematical programming},
  volume={45},
  number={1},
  pages={503--528},
  year={1989},
  publisher={Springer}
}

@incollection{bottou2010large,
  title={Large-scale machine learning with stochastic gradient descent},
  author={Bottou, L{\'e}on},
  booktitle={Proceedings of COMPSTAT'2010},
  pages={177--186},
  year={2010},
  publisher={Springer}
}

@book{thompson2015mathematical,
  title={Mathematical statistical mechanics},
  author={Thompson, Colin J},
  year={2015},
  publisher={Princeton University Press}
}

@inproceedings{li2014efficient,
  title={Efficient mini-batch training for stochastic optimization},
  author={Li, Mu and Zhang, Tong and Chen, Yuqiang and Smola, Alexander J},
  booktitle={Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining},
  pages={661--670},
  year={2014}
}

@article{frazier2018tutorial,
  title={A tutorial on Bayesian optimization},
  author={Frazier, Peter I},
  journal={arXiv preprint arXiv:1807.02811},
  year={2018}
}

@article{izmailov2018averaging,
  title={Averaging weights leads to wider optima and better generalization},
  author={Izmailov, Pavel and Podoprikhin, Dmitrii and Garipov, Timur and Vetrov, Dmitry and Wilson, Andrew Gordon},
  journal={arXiv preprint arXiv:1803.05407},
  year={2018}
}

@article{frankle2018lottery,
  title={The lottery ticket hypothesis: Finding sparse, trainable neural networks},
  author={Frankle, Jonathan and Carbin, Michael},
  journal={arXiv preprint arXiv:1803.03635},
  year={2018}
}

@inproceedings{vapnik1992principles,
  title={Principles of risk minimization for learning theory},
  author={Vapnik, Vladimir},
  booktitle={Advances in neural information processing systems},
  pages={831--838},
  year={1992}
}

@inproceedings{long2015fully,
  title={Fully convolutional networks for semantic segmentation},
  author={Long, Jonathan and Shelhamer, Evan and Darrell, Trevor},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={3431--3440},
  year={2015}
}

@book{Rudin73,
  Address =	 {New York},
  Author =	 {W.~Rudin},
  Publisher =	 {McGraw-Hill},
  Title =	 {Functional Analysis},
  Year =	 1973
}

@book{hartleyzisserman2000,
  author={Hartley, Richard and Zisserman, Andrew},
  title={Multiple View Geometry in Computer Vision},
  year={2000},
  publisher={Cambridge University Press}
}

@article{goyal2021non,
  title={Non-deep Networks},
  author={Goyal, Ankit and Bochkovskiy, Alexey and Deng, Jia and Koltun, Vladlen},
  journal={arXiv preprint arXiv:2110.07641},
  year={2021}
}

@inproceedings{jia2014caffe,
  title={Caffe: Convolutional architecture for fast feature embedding},
  author={Jia, Yangqing and Shelhamer, Evan and Donahue, Jeff and Karayev, Sergey and Long, Jonathan and Girshick, Ross and Guadarrama, Sergio and Darrell, Trevor},
  booktitle={Proceedings of the 22nd ACM international conference on Multimedia},
  pages={675--678},
  year={2014}
}

@article{mead1980introduction,
  title={Introduction to VLSI systems},
  author={Mead, Carver},
  journal={IEE Proceedings I-Solid-State and Electron Devices},
  volume={128},
  number={1},
  pages={18},
  year={1980},
  publisher={IET}
}

@inproceedings{bergstra2010theano,
  title={Theano: A CPU and GPU math compiler in Python},
  author={Bergstra, James and Breuleux, Olivier and Bastien, Fr{\'e}d{\'e}ric and Lamblin, Pascal and Pascanu, Razvan and Desjardins, Guillaume and Turian, Joseph and Warde-Farley, David and Bengio, Yoshua},
  booktitle={Proc. 9th python in science conf},
  volume={1},
  pages={3--10},
  year={2010}
}

@inproceedings{abadi2016tensorflow,
  title={Tensorflow: A system for large-scale machine learning},
  author={Abadi, Mart{\'\i}n and Barham, Paul and Chen, Jianmin and Chen, Zhifeng and Davis, Andy and Dean, Jeffrey and Devin, Matthieu and Ghemawat, Sanjay and Irving, Geoffrey and Isard, Michael and others},
  booktitle={12th $\{$USENIX$\}$ symposium on operating systems design and implementation ($\{$OSDI$\}$ 16)},
  pages={265--283},
  year={2016}
}

@article{paszke2019pytorch,
  title={Pytorch: An imperative style, high-performance deep learning library},
  author={Paszke, Adam and Gross, Sam and Massa, Francisco and Lerer, Adam and Bradbury, James and Chanan, Gregory and Killeen, Trevor and Lin, Zeming and Gimelshein, Natalia and Antiga, Luca and others},
  journal={Advances in neural information processing systems},
  volume={32},
  pages={8026--8037},
  year={2019}
}

@article{frostig2018compiling,
  title={Compiling machine learning programs via high-level tracing},
  author={Frostig, Roy and Johnson, Matthew James and Leary, Chris},
  journal={Systems for Machine Learning},
  year={2018}
}

@article{chen2015mxnet,
  title={Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems},
  author={Chen, Tianqi and Li, Mu and Li, Yutian and Lin, Min and Wang, Naiyan and Wang, Minjie and Xiao, Tianjun and Xu, Bing and Zhang, Chiyuan and Zhang, Zheng},
  journal={arXiv preprint arXiv:1512.01274},
  year={2015}
}

@phdthesis{speelpenning1980compiling,
  title={Compiling fast partial derivatives of functions given by algorithms},
  author={Speelpenning, Bert},
  year={1980},
  school={University of Illinois at Urbana-Champaign}
}

@article{kolmogorov1933sulla,
  title={Sulla determinazione empirica di una lgge di distribuzione},
  author={Kolmogorov, Andrey},
  journal={Inst. Ital. Attuari, Giorn.},
  volume={4},
  pages={83--91},
  year={1933}
}

@article{radhakrishna1945information,
  title={Information and accuracy attainable in the estimation of statistical parameters},
  author={Radhakrishna Rao, C},
  journal={Bulletin of the Calcutta Mathematical Society},
  volume={37},
  number={3},
  pages={81--91},
  year={1945},
  publisher={Calcutta Mathematical Society}
}

@article{cramer1946mathematical,
  title={Mathematical methods of statistics.},
  author={Cram{\'e}r, H},
  journal={Mathematical methods of statistics.},
  year={1946},
  publisher={Princeton University Press}
}

@article{zhang2004statistical,
  title={Statistical behavior and consistency of classification methods based on convex risk minimization},
  author={Zhang, Tong},
  journal={The Annals of Statistics},
  volume={32},
  number={1},
  pages={56--85},
  year={2004},
  publisher={Institute of Mathematical Statistics}
}

@inproceedings{ILSVRCanalysis_ICCV2013,
 author = "Olga Russakovsky and Jia Deng and Zhiheng Huang and Alexander C. Berg and Li Fei-Fei",
 title = "Detecting avocados to zucchinis: what have we done, and where are we going?",
 booktitle = "International Conference on Computer Vision (ICCV)",
 year = "2013"
}

@book{fernando2004gpu,
  title={GPU gems: programming techniques, tips, and tricks for real-time graphics},
  author={Fernando, Randima},
  volume={590},
  year={2004},
  publisher={Addison-Wesley Reading}
}

@article{buslaev2020albumentations,
  title={Albumentations: fast and flexible image augmentations},
  author={Buslaev, Alexander and Iglovikov, Vladimir I and Khvedchenya, Eugene and Parinov, Alex and Druzhinin, Mikhail and Kalinin, Alexandr A},
  journal={Information},
  volume={11},
  number={2},
  pages={125},
  year={2020},
  publisher={Multidisciplinary Digital Publishing Institute}
}

@article{torralba2008,
  title={80 million tiny images: A large data set for nonparametric object and scene recognition},
  author={Torralba, Antonio and Fergus, Rob and Freeman, William T},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  volume={30},
  number={11},
  pages={1958--1970},
  year={2008},
  publisher={IEEE}
}

@book{wasserman2013all,
  title={All of statistics: a concise course in statistical inference},
  author={Wasserman, Larry},
  year={2013},
  publisher={Springer Science \& Business Media}
}

@book{spiegelhalter2019art,
  title={The art of statistics: Learning from data},
  author={Spiegelhalter, David},
  year={2019},
  publisher={Penguin UK}
}

@article{tsoumakas2007multi,
  title={Multi-label classification: An overview},
  author={Tsoumakas, Grigorios and Katakis, Ioannis},
  journal={International Journal of Data Warehousing and Mining (IJDWM)},
  volume={3},
  number={3},
  pages={1--13},
  year={2007},
  publisher={IGI Global}
}

@article{huang2015bidirectional,
  title={Bidirectional LSTM-CRF models for sequence tagging},
  author={Huang, Zhiheng and Xu, Wei and Yu, Kai},
  journal={arXiv preprint arXiv:1508.01991},
  year={2015}
}

@inproceedings{beutel2014cobafi,
  title={Cobafi: collaborative bayesian filtering},
  author={Beutel, Alex and Murray, Kenton and Faloutsos, Christos and Smola, Alexander J},
  booktitle={Proceedings of the 23rd international conference on World wide web},
  pages={97--108},
  year={2014}
}

@inproceedings{moon2010intervalrank,
  title={Intervalrank: isotonic regression with listwise and pairwise constraints},
  author={Moon, Taesup and Smola, Alex and Chang, Yi and Zheng, Zhaohui},
  booktitle={Proceedings of the third ACM international conference on Web search and data mining},
  pages={151--160},
  year={2010}
}

@article{shannon1948mathematical,
  title={A mathematical theory of communication},
  author={Shannon, Claude Elwood},
  journal={The Bell system technical journal},
  volume={27},
  number={3},
  pages={379--423},
  year={1948},
  publisher={Nokia Bell Labs}
}

@book{cover1999elements,
  title={Elements of information theory},
  author={T. Cover and J.M. Thomas},
  year={1999},
  publisher={John Wiley \& Sons}
}

@inproceedings{ranzato2007unified,
  title={A unified energy-based framework for unsupervised learning},
  author={Ranzato, Marc’Aurelio and Boureau, Y-Lan and Chopra, Sumit and LeCun, Yann},
  booktitle={Artificial Intelligence and Statistics},
  pages={371--379},
  year={2007},
  organization={PMLR}
}

@inproceedings{lecun1995comparison,
  title={Comparison of learning algorithms for handwritten digit recognition},
  author={LeCun, Yann and Jackel, LD and Bottou, Leon and Brunot, A and Cortes, Corinna and Denker, John and Drucker, Harris and Guyon, Isabelle and Muller, UA and Sackinger, Eduard and others},
  booktitle={International conference on artificial neural networks},
  volume={60},
  pages={53--60},
  year={1995},
  organization={Perth, Australia}
}

@inproceedings{scholkopf1996incorporating,
  title={Incorporating invariances in support vector learning machines},
  author={Sch{\"o}lkopf, Bernhard and Burges, Chris and Vapnik, Vladimir},
  booktitle={International Conference on Artificial Neural Networks},
  pages={47--52},
  year={1996},
  organization={Springer}
}

@incollection{simard1998transformation,
  title={Transformation invariance in pattern recognition—tangent distance and tangent propagation},
  author={Simard, Patrice Y and LeCun, Yann A and Denker, John S and Victorri, Bernard},
  booktitle={Neural networks: tricks of the trade},
  pages={239--274},
  year={1998},
  publisher={Springer}
}

@article{gibbs1902elementary,
  title={Elementary Principles of Statistical Mechanics},
  author={Gibbs, Josiah Willard},
  journal={Compare},
  volume={289},
  pages={314},
  year={1902}
}

@book{fechner1860elemente,
  title={Elemente der Ppsychophysik},
  author={Fechner, Gustav Theodor},
  volume={2},
  year={1860},
  publisher={Breitkopf u. H{\"a}rtel}
}

@article{bradley1952rank,
  title={Rank analysis of incomplete block designs: I. The method of paired comparisons},
  author={Bradley, Ralph Allan and Terry, Milton E},
  journal={Biometrika},
  volume={39},
  number={3/4},
  pages={324--345},
  year={1952},
  publisher={JSTOR}
}

@inproceedings{yang2015deep,
  title={Deep fried convnets},
  author={Yang, Zichao and Moczulski, Marcin and Denil, Misha and De Freitas, Nando and Smola, Alex and Song, Le and Wang, Ziyu},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={1476--1483},
  year={2015}
}

@article{ramachandran2017searching,
  title={Searching for activation functions},
  author={Ramachandran, Prajit and Zoph, Barret and Le, Quoc V},
  journal={arXiv preprint arXiv:1710.05941},
  year={2017}
}

@book{fisher1928statistical,
  title={Statistical methods for research workers.},
  author={Fisher, RA},
  year={1928},
  publisher={Stechert}
}

@article{aronszajn1950theory,
  title={Theory of reproducing kernels},
  author={Aronszajn, Nachman},
  journal={Transactions of the American mathematical society},
  volume={68},
  number={3},
  pages={337--404},
  year={1950}
}

@book{wahba1990spline,
  title={Spline models for observational data},
  author={Wahba, Grace},
  year={1990},
  publisher={SIAM}
}

@article{cybenko1989approximation,
  title={Approximation by superpositions of a sigmoidal function},
  author={Cybenko, George},
  journal={Mathematics of control, signals and systems},
  volume={2},
  number={4},
  pages={303--314},
  year={1989},
  publisher={Springer}
}

@article{Micchelli86,
  Author =	 {C.~A.~Micchelli},
  Journal =	 {Proceedings of Symposia in Applied Mathematics},
  Pages =	 {81-102},
  Title =	 {Algebraic aspects of interpolation},
  Volume =	 36,
  Year =	 1986
}

@inproceedings{SchHerSmo01,
  Address =	 {London, UK},
  Author =	 {B.~Sch{\"o}lkopf and R.~Herbrich and A. J. Smola},
  Booktitle =	 {Proc.\ Annual Conf.\ Computational Learning Theory},
  Editor =	 {D.~P.~Helmbold and B.~Williamson},
  Number =	 2111,
  Pages =	 {416-426},
  Publisher =	 {Springer-Verlag},
  Series =	 {Lecture Notes in Comput. Sci.},
  Title =	 {A Generalized Representer Theorem},
  Year =	 2001
}

@article{KimWah71,
  Author =	 {G.~S.~Kimeldorf and G.~Wahba},
  Journal =	 {J.~Math.~Anal.~Appl.},
  Pages =	 {82-95},
  Title =	 {Some Results on {T}chebycheffian Spline Functions},
  Volume =	 33,
  Year =	 1971
}

@inproceedings{nair2010rectified,
  title={Rectified linear units improve restricted boltzmann machines},
  author={Nair, Vinod and Hinton, Geoffrey E},
  booktitle={Icml},
  year={2010}
}

@book{ramonycajal1894nouvelles,
  title={Les nouvelles id{\'e}es sur la structure du syst{\`e}me nerveux chez l'homme et chez les vert{\'e}br{\'e}s},
  author={y Cajal, Santiago Ram{\'o}n and Azoulay, L{\'e}on},
  year={1894},
  publisher={C. Reinwald}
}

@incollection{prechelt1998early,
  title={Early stopping-but when?},
  author={Prechelt, Lutz},
  booktitle={Neural Networks: Tricks of the trade},
  pages={55--69},
  year={1998},
  publisher={Springer}
}

@article{vapnik1994measuring,
  title={Measuring the VC-dimension of a learning machine},
  author={Vapnik, Vladimir and Levin, Esther and Le Cun, Yann},
  journal={Neural computation},
  volume={6},
  number={5},
  pages={851--876},
  year={1994},
  publisher={MIT Press}
}

@article{corfield2009falsificationism,
  title={Falsificationism and statistical learning theory: Comparing the Popper and Vapnik-Chervonenkis dimensions},
  author={Corfield, David and Sch{\"o}lkopf, Bernhard and Vapnik, Vladimir},
  journal={Journal for General Philosophy of Science},
  volume={40},
  number={1},
  pages={51--58},
  year={2009},
  publisher={Springer}
}

@article{murata1994network,
  title={Network information criterion-determining the number of hidden units for an artificial neural network model},
  author={Murata, Noboru and Yoshizawa, Shuji and Amari, Shun-ichi},
  journal={IEEE transactions on neural networks},
  volume={5},
  number={6},
  pages={865--872},
  year={1994},
  publisher={IEEE}
}

@inproceedings{krogh1992simple,
  title={A simple weight decay can improve generalization},
  author={Krogh, Anders and Hertz, John A},
  booktitle={Advances in neural information processing systems},
  pages={950--957},
  year={1992}
}

@article{henighan2020scaling,
  title={Scaling laws for autoregressive generative modeling},
  author={Henighan, Tom and Kaplan, Jared and Katz, Mor and Chen, Mark and Hesse, Christopher and Jackson, Jacob and Jun, Heewoo and Brown, Tom B and Dhariwal, Prafulla and Gray, Scott and others},
  journal={arXiv preprint arXiv:2010.14701},
  year={2020}
}

@article{friedman1987exploratory,
  title={Exploratory projection pursuit},
  author={Friedman, Jerome H},
  journal={Journal of the American statistical association},
  volume={82},
  number={397},
  pages={249--266},
  year={1987},
  publisher={Taylor \& Francis}
}

@book{cherubini2004copula,
  title={Copula methods in finance},
  author={Cherubini, Umberto and Luciano, Elisa and Vecchiato, Walter},
  year={2004},
  publisher={John Wiley \& Sons}
}

@inproceedings{radosavovic2020designing,
  title={Designing network design spaces},
  author={Radosavovic, Ilija and Kosaraju, Raj Prateek and Girshick, Ross and He, Kaiming and Doll{\'a}r, Piotr},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={10428--10436},
  year={2020}
}

@article{ong2005learning,
  title={Learning the kernel with hyperkernels},
  author={Ong, Cheng Soon and Smola, Alexander and Williamson, Robert and others},
  year={2005},
  publisher={MIT Press},
  journal={Journal of Machine Learning Research}
}

@article{koller2004max,
  title={Max-margin Markov networks},
  author={Taskar, Ben and Guestrin, Carlos and Koller, Daphne},
  journal={Advances in neural information processing systems},
  volume={16},
  pages={25},
  year={2004}
}

@inproceedings{freund1996experiments,
  title={Experiments with a new boosting algorithm},
  author={Freund, Yoav and Schapire, Robert E and others},
  booktitle={icml},
  volume={96},
  pages={148--156},
  year={1996},
  organization={Citeseer}
}

@book{scholkopf2002learning,
  title={Learning with kernels: support vector machines, regularization, optimization, and beyond},
  author={Scholkopf, Bernhard and Smola, Alexander J},
  year={2002},
  publisher={Adaptive Computation and Machine Learning Series}
}

@misc{quinlan1993c4,
  title={C4. 5: programs for machine learning},
  author={Quinlan, J Ross},
  year={1993},
  publisher={Morgan Kaufmann Publishers Inc.}
}

@article{thomee2016yfcc100m,
  title={YFCC100M: The new data in multimedia research},
  author={Thomee, Bart and Shamma, David A and Friedland, Gerald and Elizalde, Benjamin and Ni, Karl and Poland, Douglas and Borth, Damian and Li, Li-Jia},
  journal={Communications of the ACM},
  volume={59},
  number={2},
  pages={64--73},
  year={2016},
  publisher={ACM New York, NY, USA}
}

@book{Vapnik98,
  Address =	 {New York},
  Author =	 {V. Vapnik},
  Publisher =	 {John Wiley and Sons},
  Title =	 {Statistical Learning Theory},
  Year =	 1998
}

@article{Glivenko33,
  Author =	 {V.~I. Glivenko},
  Journal =	 {Giornale dell'Istituta Italiano degli Attuari},
  Pages =	 92,
  Title =	 {Sulla determinazione empirica delle leggi di
                  probabilita},
  Volume =	 4,
  Year =	 1933
}

@article{Cantelli33,
  Author =	 {F.~P. Cantelli},
  Journal =	 {Rend.\ Accad.\ Lincei},
  Number =	 1,
  Pages =	 39,
  Title =	 {Sulla probabilita come limita della frequenza},
  Volume =	 26,
  Year =	 1933
}

@article{VapChe64,
  Author =	 {V. Vapnik and A. Chervonenkis},
  Issue =	 1,
  Journal =	 {Automation and Remote Control},
  Title =	 {A note on one class of perceptrons},
  Volume =	 25,
  Year =	 1964
}

@article{VapChe68,
  Author =	 {V. Vapnik and A. Chervonenkis},
  Journal =	 {Dokl.\ Akad.\ Nauk SSSR},
  Pages =	 {915-918},
  Title =	 {Uniform convergence of frequencies of occurence of
                  events to their probabilities},
  Volume =	 181,
  Year =	 1968
}

@article{VapChe71,
  Author =	 {V. Vapnik and A. Chervonenkis},
  Journal =	 {Theory Probab. Appl.},
  Number =	 2,
  Pages =	 {264-281},
  Title =	 {On the uniform convergence of relative frequencies
                  of events to their probabilities},
  Volume =	 16,
  Year =	 1971
}

@book{VapChe74,
  Address =	 {Moscow},
  Author =	 {V. Vapnik and A. Chervonenkis},
  Note =	 {(German Translation: W. Wapnik \& A. Tscherwonenkis,
                  {\em Theorie der Zeichenerkennung}, Akademie-Verlag,
                  Berlin, 1979)},
  Publisher =	 {Nauka},
  Title =	 {Theory of Pattern Recognition [in Russian]},
  Year =	 1974
}

@article{VapChe74b,
  Author =	 {V.~N. Vapnik and A.~Y. Chervonenkis},
  Journal =	 {Automation and Remote Control},
  Pages =	 {1226--1235, 1403--1412},
  Title =	 {Ordered risk minimization},
  Volume =	 35,
  Year =	 1974
}

@book{VapChe74c,
  Address =	 {Moscow: Nauka},
  Author =	 {V. Vapnik and A. Chervonenkis},
  Title =	 {Teoriya raspoznavaniya obrazov: Statisticheskie
                  problemy obucheniya. (Russian) [Theory of pattern
                  recognition: Statistical problems of learning]},
  Year =	 1974
}

@article{VapChe81,
  Author =	 {V. Vapnik and A. Chervonenkis},
  Journal =	 {Teoriya Veroyatnostei i Ee Primeneniya},
  Number =	 3,
  Pages =	 {543-564},
  Title =	 {The necessary and sufficient conditions for the
                  uniform convergence of averages to their expected
                  values},
  Volume =	 26,
  Year =	 1981
}

@article{VapChe91,
  Author =	 {V. Vapnik and A. Chervonenkis},
  Journal =	 {Pattern Recognition and Image Analysis},
  Number =	 3,
  Pages =	 {283-305},
  Title =	 {The necessary and sufficient conditions for
                  consistency in the empirical risk minimization
                  method},
  Volume =	 1,
  Year =	 1991
}

@article{rosenbaum1983central,
  title={The central role of the propensity score in observational studies for causal effects},
  author={Rosenbaum, Paul R and Rubin, Donald B},
  journal={Biometrika},
  volume={70},
  number={1},
  pages={41--55},
  year={1983},
  publisher={Oxford University Press}
}

@article{yu1994rates,
  title={Rates of convergence for empirical processes of stationary mixing sequences},
  author={Yu, Bin},
  journal={The Annals of Probability},
  pages={94--116},
  year={1994},
  publisher={JSTOR}
}

@article{bartlett2021deep,
  title={Deep learning: a statistical viewpoint},
  author={Bartlett, Peter L and Montanari, Andrea and Rakhlin, Alexander},
  journal={arXiv preprint arXiv:2103.09177},
  year={2021}
}

@article{nagarajan2019uniform,
  title={Uniform convergence may be unable to explain generalization in deep learning},
  author={Nagarajan, Vaishnavh and Kolter, J Zico},
  journal={arXiv preprint arXiv:1902.04742},
  year={2019}
}

@article{kawaguchi2017generalization,
  title={Generalization in deep learning},
  author={Kawaguchi, Kenji and Kaelbling, Leslie Pack and Bengio, Yoshua},
  journal={arXiv preprint arXiv:1710.05468},
  year={2017}
}


@article{friedman1997bias,
  title={On bias, variance, 0/1—loss, and the curse-of-dimensionality},
  author={Friedman, Jerome H},
  journal={Data mining and knowledge discovery},
  volume={1},
  number={1},
  pages={55--77},
  year={1997},
  publisher={Springer}
}

@article{boucheron2005theory,
  title={Theory of classification: A survey of some recent advances},
  author={Boucheron, St{\'e}phane and Bousquet, Olivier and Lugosi, G{\'a}bor},
  journal={ESAIM: probability and statistics},
  volume={9},
  pages={323--375},
  year={2005},
  publisher={EDP Sciences}
}

@article{der2009aleatory,
  title={Aleatory or epistemic? Does it matter?},
  author={Der Kiureghian, Armen and Ditlevsen, Ove},
  journal={Structural safety},
  volume={31},
  number={2},
  pages={105--112},
  year={2009},
  publisher={Elsevier}
}

@article{sindhwani2015structured,
  title={Structured transforms for small-footprint deep learning},
  author={Sindhwani, Vikas and Sainath, Tara N and Kumar, Sanjiv},
  journal={arXiv preprint arXiv:1510.01722},
  year={2015}
}

@inproceedings{dwork2015preserving,
  title={Preserving statistical validity in adaptive data analysis},
  author={Dwork, Cynthia and Feldman, Vitaly and Hardt, Moritz and Pitassi, Toniann and Reingold, Omer and Roth, Aaron Leon},
  booktitle={Proceedings of the forty-seventh annual ACM symposium on Theory of computing},
  pages={117--126},
  year={2015}
}

@book{quinlan2014c4,
  title={C4. 5: programs for machine learning},
  author={Quinlan, J Ross},
  year={2014},
  publisher={Elsevier}
}

@incollection{micchelli1984interpolation,
  title={Interpolation of scattered data: distance matrices and conditionally positive definite functions},
  author={Micchelli, Charles A},
  booktitle={Approximation theory and spline functions},
  pages={143--145},
  year={1984},
  publisher={Springer}
}

@book{popper2005logic,
  title={The logic of scientific discovery},
  author={Popper, Karl},
  year={2005},
  publisher={Routledge}
}

@book{mackay2003information,
  title={Information theory, inference and learning algorithms},
  author={MacKay, David JC and Mac Kay, David JC},
  year={2003},
  publisher={Cambridge university press}
}

@book{rasmussen2006gaussian,
  title={Gaussian processes for machine learning},
  author={Rasmussen, Carl Edward and Williams, Christopher KI},
  volume={2},
  number={3},
  year={2006},
  publisher={MIT press}
}


@inproceedings{lavin2016fast,
  title={Fast algorithms for convolutional neural networks},
  author={Lavin, Andrew and Gray, Scott},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={4013--4021},
  year={2016}
}

@inproceedings{tan2019efficientnet,
  title={Efficientnet: Rethinking model scaling for convolutional neural networks},
  author={Tan, Mingxing and Le, Quoc},
  booktitle={International conference on machine learning},
  pages={6105--6114},
  year={2019},
  organization={PMLR}
}

@article{zoph2016neural,
  title={Neural architecture search with reinforcement learning},
  author={Zoph, Barret and Le, Quoc V},
  journal={arXiv preprint arXiv:1611.01578},
  year={2016}
}

@article{liu2018darts,
  title={Darts: Differentiable architecture search},
  author={Liu, Hanxiao and Simonyan, Karen and Yang, Yiming},
  journal={arXiv preprint arXiv:1806.09055},
  year={2018}
}

@article{liu2022convnet,
  title={A ConvNet for the 2020s},
  author={Liu, Zhuang and Mao, Hanzi and Wu, Chao-Yuan and Feichtenhofer, Christoph and Darrell, Trevor and Xie, Saining},
  journal={arXiv preprint arXiv:2201.03545},
  year={2022}
}

@inproceedings{radosavovic2019network,
  title={On network design spaces for visual recognition},
  author={Radosavovic, Ilija and Johnson, Justin and Xie, Saining and Lo, Wan-Yen and Doll{\'a}r, Piotr},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={1882--1890},
  year={2019}
}

@article{tolstikhin2021mlp,
  title={Mlp-mixer: An all-mlp architecture for vision},
  author={Tolstikhin, Ilya O and Houlsby, Neil and Kolesnikov, Alexander and Beyer, Lucas and Zhai, Xiaohua and Unterthiner, Thomas and Yung, Jessica and Steiner, Andreas and Keysers, Daniel and Uszkoreit, Jakob and others},
  journal={Advances in Neural Information Processing Systems},
  volume={34},
  year={2021}
}

@inproceedings{liu2021swin,
  title={Swin transformer: Hierarchical vision transformer using shifted windows},
  author={Liu, Ze and Lin, Yutong and Cao, Yue and Hu, Han and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Guo, Baining},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={10012--10022},
  year={2021}
}

@inproceedings{touvron2021training,
  title={Training data-efficient image transformers \& distillation through attention},
  author={Touvron, Hugo and Cord, Matthieu and Douze, Matthijs and Massa, Francisco and Sablayrolles, Alexandre and J{\'e}gou, Herv{\'e}},
  booktitle={International Conference on Machine Learning},
  pages={10347--10357},
  year={2021},
  organization={PMLR}
}

@inproceedings{huang2018music,
  title={Music Transformer: Generating Music with Long-Term Structure},
  author={Huang, Cheng-Zhi Anna and Vaswani, Ashish and Uszkoreit, Jakob and Simon, Ian and Hawthorne, Curtis and Shazeer, Noam and Dai, Andrew M and Hoffman, Matthew D and Dinculescu, Monica and Eck, Douglas},
  booktitle={International Conference on Learning Representations},
  year={2018}
}

@article{shaw2018self,
  title={Self-attention with relative position representations},
  author={Shaw, Peter and Uszkoreit, Jakob and Vaswani, Ashish},
  journal={arXiv preprint arXiv:1803.02155},
  year={2018}
}

@book{neal1996bayesian,
  title={Bayesian learning for neural networks},
  author={Neal, Radford M},
  year={1996},
  publisher={Springer Science \& Business Media}
}

@article{matthews2018gaussian,
  title={Gaussian process behaviour in wide deep neural networks},
  author={Matthews, Alexander G de G and Rowland, Mark and Hron, Jiri and Turner, Richard E and Ghahramani, Zoubin},
  journal={arXiv preprint arXiv:1804.11271},
  year={2018}
}

@article{novak2018bayesian,
  title={Bayesian deep convolutional networks with many channels are {G}aussian processes},
  author={Novak, Roman and Xiao, Lechao and Lee, Jaehoon and Bahri, Yasaman and Yang, Greg and Hron, Jiri and Abolafia, Daniel A and Pennington, Jeffrey and Sohl-Dickstein, Jascha},
  journal={arXiv preprint arXiv:1810.05148},
  year={2018}
}

@article{zhang2021understanding,
  title={Understanding deep learning (still) requires rethinking generalization},
  author={Zhang, Chiyuan and Bengio, Samy and Hardt, Moritz and Recht, Benjamin and Vinyals, Oriol},
  journal={Communications of the ACM},
  volume={64},
  number={3},
  pages={107--115},
  year={2021},
  publisher={ACM New York, NY, USA}
}

@article{nakkiran2021deep,
  title={Deep double descent: Where bigger models and more data hurt},
  author={Nakkiran, Preetum and Kaplun, Gal and Bansal, Yamini and Yang, Tristan and Barak, Boaz and Sutskever, Ilya},
  journal={Journal of Statistical Mechanics: Theory and Experiment},
  volume={2021},
  number={12},
  pages={124003},
  year={2021},
  publisher={IOP Publishing}
}

@book{tikhonov1977solutions,
  title={Solutions of ill-posed problems},
  author={Tikhonov, A. N. and Arsenin, V. Y.},
  year={1977},
  publisher={W.H.~Winston}
}

@book{morozov2012methods,
  title={Methods for solving incorrectly posed problems},
  author={Morozov, Vladimir Alekseevich},
  year={1984},
  publisher={Springer Science \& Business Media}
}

@article{srivastava2015highway,
  title={Highway networks},
  author={Srivastava, Rupesh Kumar and Greff, Klaus and Schmidhuber, J{\"u}rgen},
  journal={arXiv preprint arXiv:1505.00387},
  year={2015}
}

@article{pleiss2017memory,
  title={Memory-efficient implementation of densenets},
  author={Pleiss, Geoff and Chen, Danlu and Huang, Gao and Li, Tongcheng and Van Der Maaten, Laurens and Weinberger, Kilian Q},
  journal={arXiv preprint arXiv:1707.06990},
  year={2017}
}

@article{ramachandran2019stand,
  title={Stand-alone self-attention in vision models},
  author={Ramachandran, Prajit and Parmar, Niki and Vaswani, Ashish and Bello, Irwan and Levskaya, Anselm and Shlens, Jon},
  journal={Advances in Neural Information Processing Systems},
  volume={32},
  year={2019}
}


@inproceedings{cordonnier2020relationship,
  title={On the Relationship between Self-Attention and Convolutional Layers},
  author={Cordonnier, Jean-Baptiste and Loukas, Andreas and Jaggi, Martin},
  booktitle={International Conference on Learning Representations},
  year={2020}
}

@article{brown2020language,
  title={Language models are few-shot learners},
  author={Brown, Tom and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared D and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and others},
  journal={Advances in neural information processing systems},
  volume={33},
  pages={1877--1901},
  year={2020}
}

@article{raffel2020exploring,
  title={Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer},
  author={Raffel, Colin and Shazeer, Noam and Roberts, Adam and Lee, Katherine and Narang, Sharan and Matena, Michael and Zhou, Yanqi and Li, Wei and Liu, Peter J},
  journal={Journal of Machine Learning Research},
  volume={21},
  pages={1--67},
  year={2020}
}

@article{hendrycks2016gaussian,
  title={Gaussian error linear units (gelus)},
  author={Hendrycks, Dan and Gimpel, Kevin},
  journal={arXiv preprint arXiv:1606.08415},
  year={2016}
}

@inproceedings{xiong2020layer,
  title={On layer normalization in the transformer architecture},
  author={Xiong, Ruibin and Yang, Yunchang and He, Di and Zheng, Kai and Zheng, Shuxin and Xing, Chen and Zhang, Huishuai and Lan, Yanyan and Wang, Liwei and Liu, Tieyan},
  booktitle={International Conference on Machine Learning},
  pages={10524--10533},
  year={2020},
  organization={PMLR}
}

@inproceedings{baevski2018adaptive,
  title={Adaptive Input Representations for Neural Language Modeling},
  author={Baevski, Alexei and Auli, Michael},
  booktitle={International Conference on Learning Representations},
  year={2018}
}

@inproceedings{wang2019learning,
  title={Learning Deep Transformer Models for Machine Translation},
  author={Wang, Qiang and Li, Bei and Xiao, Tong and Zhu, Jingbo and Li, Changliang and Wong, Derek F and Chao, Lidia S},
  booktitle={Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  pages={1810--1822},
  year={2019}
}

@article{wilson2020bayesian,
  title={Bayesian deep learning and a probabilistic perspective of generalization},
  author={Wilson, Andrew G and Izmailov, Pavel},
  journal={Advances in neural information processing systems},
  volume={33},
  pages={4697--4708},
  year={2020}
}

@article{lewis2019bart,
  title={Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension},
  author={Lewis, Mike and Liu, Yinhan and Goyal, Naman and Ghazvininejad, Marjan and Mohamed, Abdelrahman and Levy, Omer and Stoyanov, Ves and Zettlemoyer, Luke},
  journal={arXiv preprint arXiv:1910.13461},
  year={2019}
}

@inproceedings{clark2019electra,
  title={ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators},
  author={Clark, Kevin and Luong, Minh-Thang and Le, Quoc V and Manning, Christopher D},
  booktitle={International Conference on Learning Representations},
  year={2020}
}

@article{yang2019xlnet,
  title={Xlnet: Generalized autoregressive pretraining for language understanding},
  author={Yang, Zhilin and Dai, Zihang and Yang, Yiming and Carbonell, Jaime and Salakhutdinov, Russ R and Le, Quoc V},
  journal={Advances in neural information processing systems},
  volume={32},
  year={2019}
}

@article{lan2019albert,
  title={Albert: A lite bert for self-supervised learning of language representations},
  author={Lan, Zhenzhong and Chen, Mingda and Goodman, Sebastian and Gimpel, Kevin and Sharma, Piyush and Soricut, Radu},
  journal={arXiv preprint arXiv:1909.11942},
  year={2019}
}

@article{sanh2019distilbert,
  title={DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter},
  author={Sanh, Victor and Debut, Lysandre and Chaumond, Julien and Wolf, Thomas},
  journal={arXiv preprint arXiv:1910.01108},
  year={2019}
}

@inproceedings{he2022masked,
  title={Masked autoencoders are scalable vision learners},
  author={He, Kaiming and Chen, Xinlei and Xie, Saining and Li, Yanghao and Doll{\'a}r, Piotr and Girshick, Ross},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={16000--16009},
  year={2022}
}

@inproceedings{chen2020generative,
  title={Generative pretraining from pixels},
  author={Chen, Mark and Radford, Alec and Child, Rewon and Wu, Jeffrey and Jun, Heewoo and Luan, David and Sutskever, Ilya},
  booktitle={International conference on machine learning},
  pages={1691--1703},
  year={2020},
  organization={PMLR}
}

@article{liu2019roberta,
  title={Roberta: A robustly optimized bert pretraining approach},
  author={Liu, Yinhan and Ott, Myle and Goyal, Naman and Du, Jingfei and Joshi, Mandar and Chen, Danqi and Levy, Omer and Lewis, Mike and Zettlemoyer, Luke and Stoyanov, Veselin},
  journal={arXiv preprint arXiv:1907.11692},
  year={2019}
}

@article{kaplan2020scaling,
  title={Scaling laws for neural language models},
  author={Kaplan, Jared and McCandlish, Sam and Henighan, Tom and Brown, Tom B and Chess, Benjamin and Child, Rewon and Gray, Scott and Radford, Alec and Wu, Jeffrey and Amodei, Dario},
  journal={arXiv preprint arXiv:2001.08361},
  year={2020}
}

@article{rae2021scaling,
  title={Scaling language models: Methods, analysis \& insights from training gopher},
  author={Rae, Jack W and Borgeaud, Sebastian and Cai, Trevor and Millican, Katie and Hoffmann, Jordan and Song, Francis and Aslanides, John and Henderson, Sarah and Ring, Roman and Young, Susannah and others},
  journal={arXiv preprint arXiv:2112.11446},
  year={2021}
}

@article{du2021glam,
  title={Glam: Efficient scaling of language models with mixture-of-experts},
  author={Du, Nan and Huang, Yanping and Dai, Andrew M and Tong, Simon and Lepikhin, Dmitry and Xu, Yuanzhong and Krikun, Maxim and Zhou, Yanqi and Yu, Adams Wei and Firat, Orhan and others},
  journal={arXiv preprint arXiv:2112.06905},
  year={2021}
}

@article{shoeybi2019megatron,
  title={Megatron-lm: Training multi-billion parameter language models using model parallelism},
  author={Shoeybi, Mohammad and Patwary, Mostofa and Puri, Raul and LeGresley, Patrick and Casper, Jared and Catanzaro, Bryan},
  journal={arXiv preprint arXiv:1909.08053},
  year={2019}
}

@article{smith2022using,
  title={Using deepspeed and megatron to train megatron-turing nlg 530b, a large-scale generative language model},
  author={Smith, Shaden and Patwary, Mostofa and Norick, Brandon and LeGresley, Patrick and Rajbhandari, Samyam and Casper, Jared and Liu, Zhun and Prabhumoye, Shrimai and Zerveas, George and Korthikanti, Vijay and others},
  journal={arXiv preprint arXiv:2201.11990},
  year={2022}
}

@article{thoppilan2022lamda,
  title={Lamda: Language models for dialog applications},
  author={Thoppilan, Romal and De Freitas, Daniel and Hall, Jamie and Shazeer, Noam and Kulshreshtha, Apoorv and Cheng, Heng-Tze and Jin, Alicia and Bos, Taylor and Baker, Leslie and Du, Yu and others},
  journal={arXiv preprint arXiv:2201.08239},
  year={2022}
}

@article{hoffmann2022training,
  title={Training Compute-Optimal Large Language Models},
  author={Hoffmann, Jordan and Borgeaud, Sebastian and Mensch, Arthur and Buchatskaya, Elena and Cai, Trevor and Rutherford, Eliza and Casas, Diego de Las and Hendricks, Lisa Anne and Welbl, Johannes and Clark, Aidan and others},
  journal={arXiv preprint arXiv:2203.15556},
  year={2022}
}

@article{zhang2022opt,
  title={Opt: Open pre-trained transformer language models},
  author={Zhang, Susan and Roller, Stephen and Goyal, Naman and Artetxe, Mikel and Chen, Moya and Chen, Shuohui and Dewan, Christopher and Diab, Mona and Li, Xian and Lin, Xi Victoria and others},
  journal={arXiv preprint arXiv:2205.01068},
  year={2022}
}

@article{chowdhery2022palm,
  title={Palm: Scaling language modeling with pathways},
  author={Chowdhery, Aakanksha and Narang, Sharan and Devlin, Jacob and Bosma, Maarten and Mishra, Gaurav and Roberts, Adam and Barham, Paul and Chung, Hyung Won and Sutton, Charles and Gehrmann, Sebastian and others},
  journal={arXiv preprint arXiv:2204.02311},
  year={2022}
}

@article{hernandez2021scaling,
  title={Scaling laws for transfer},
  author={Hernandez, Danny and Kaplan, Jared and Henighan, Tom and McCandlish, Sam},
  journal={arXiv preprint arXiv:2102.01293},
  year={2021}
}

@article{tay2021scale,
  title={Scale efficiently: Insights from pre-training and fine-tuning transformers},
  author={Tay, Yi and Dehghani, Mostafa and Rao, Jinfeng and Fedus, William and Abnar, Samira and Chung, Hyung Won and Narang, Sharan and Yogatama, Dani and Vaswani, Ashish and Metzler, Donald},
  journal={arXiv preprint arXiv:2109.10686},
  year={2021}
}

@article{wei2022emergent,
  title={Emergent Abilities of Large Language Models},
  author={Wei, Jason and Tay, Yi and Bommasani, Rishi and Raffel, Colin and Zoph, Barret and Borgeaud, Sebastian and Yogatama, Dani and Bosma, Maarten and Zhou, Denny and Metzler, Donald and others},
  journal={arXiv preprint arXiv:2206.07682},
  year={2022}
}

@inproceedings{radford2021learning,
  title={Learning transferable visual models from natural language supervision},
  author={Radford, Alec and Kim, Jong Wook and Hallacy, Chris and Ramesh, Aditya and Goh, Gabriel and Agarwal, Sandhini and Sastry, Girish and Askell, Amanda and Mishkin, Pamela and Clark, Jack and others},
  booktitle={International Conference on Machine Learning},
  pages={8748--8763},
  year={2021},
  organization={PMLR}
}

@inproceedings{ramesh2021zero,
  title={Zero-shot text-to-image generation},
  author={Ramesh, Aditya and Pavlov, Mikhail and Goh, Gabriel and Gray, Scott and Voss, Chelsea and Radford, Alec and Chen, Mark and Sutskever, Ilya},
  booktitle={International Conference on Machine Learning},
  pages={8821--8831},
  year={2021},
  organization={PMLR}
}

@article{ramesh2022hierarchical,
  title={Hierarchical text-conditional image generation with clip latents},
  author={Ramesh, Aditya and Dhariwal, Prafulla and Nichol, Alex and Chu, Casey and Chen, Mark},
  journal={arXiv preprint arXiv:2204.06125},
  year={2022}
}

@article{alayrac2022flamingo,
  title={Flamingo: a visual language model for few-shot learning},
  author={Alayrac, Jean-Baptiste and Donahue, Jeff and Luc, Pauline and Miech, Antoine and Barr, Iain and Hasson, Yana and Lenc, Karel and Mensch, Arthur and Millican, Katie and Reynolds, Malcolm and others},
  journal={arXiv preprint arXiv:2204.14198},
  year={2022}
}

@article{saharia2022photorealistic,
  title={Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding},
  author={Saharia, Chitwan and Chan, William and Saxena, Saurabh and Li, Lala and Whang, Jay and Denton, Emily and Ghasemipour, Seyed Kamyar Seyed and Ayan, Burcu Karagol and Mahdavi, S Sara and Lopes, Rapha Gontijo and others},
  journal={arXiv preprint arXiv:2205.11487},
  year={2022}
}

@article{reed2022generalist,
  title={A generalist agent},
  author={Reed, Scott and Zolna, Konrad and Parisotto, Emilio and Colmenarejo, Sergio Gomez and Novikov, Alexander and Barth-Maron, Gabriel and Gimenez, Mai and Sulsky, Yury and Kay, Jackie and Springenberg, Jost Tobias and others},
  journal={arXiv preprint arXiv:2205.06175},
  year={2022}
}

@article{fedus2022switch,
  title={Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity},
  author={Fedus, William and Zoph, Barret and Shazeer, Noam},
  journal={Journal of Machine Learning Research},
  volume={23},
  number={120},
  pages={1--39},
  year={2022}
}

@article{child2019generating,
  title={Generating long sequences with sparse transformers},
  author={Child, Rewon and Gray, Scott and Radford, Alec and Sutskever, Ilya},
  journal={arXiv preprint arXiv:1904.10509},
  year={2019}
}

@article{joshi2020spanbert,
  title={Spanbert: Improving pre-training by representing and predicting spans},
  author={Joshi, Mandar and Chen, Danqi and Liu, Yinhan and Weld, Daniel S and Zettlemoyer, Luke and Levy, Omer},
  journal={Transactions of the Association for Computational Linguistics},
  volume={8},
  pages={64--77},
  year={2020},
  publisher={MIT Press}
}

@article{yu2022scaling,
  title={Scaling Autoregressive Models for Content-Rich Text-to-Image Generation},
  author={Yu, Jiahui and Xu, Yuanzhong and Koh, Jing Yu and Luong, Thang and Baid, Gunjan and Wang, Zirui and Vasudevan, Vijay and Ku, Alexander and Yang, Yinfei and Karagol Ayan, Burcu and Hutchinson, Ben and Han, Wei and Parekh, Zarana and Li, Xin and Zhang, Han and Baldridge, Jason and Wu, Yonghui},
  journal={arXiv preprint arXiv:2206.10789},
  year={2022}
}

@article{srivastava2022beyond,
  title={Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models},
  author={Srivastava, Aarohi and Rastogi, Abhinav and Rao, Abhishek and Shoeb, Abu Awal Md and Abid, Abubakar and Fisch, Adam and Brown, Adam R and Santoro, Adam and Gupta, Aditya and Garriga-Alonso, Adri{\`a} and others},
  journal={arXiv preprint arXiv:2206.04615},
  year={2022}
}

@article{lewkowycz2022solving,
  title={Solving Quantitative Reasoning Problems with Language Models},
  author={Lewkowycz, Aitor and Andreassen, Anders and Dohan, David and Dyer, Ethan and Michalewski, Henryk and Ramasesh, Vinay and Slone, Ambrose and Anil, Cem and Schlag, Imanol and Gutman-Solo, Theo and others},
  journal={arXiv preprint arXiv:2206.14858},
  year={2022}
}

@article{mnih2015human,
  title={Human-level control through deep reinforcement learning},
  author={Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Rusu, Andrei A and Veness, Joel and Bellemare, Marc G and Graves, Alex and Riedmiller, Martin and Fidjeland, Andreas K and Ostrovski, Georg and others},
  journal={nature},
  volume={518},
  number={7540},
  pages={529--533},
  year={2015},
  publisher={Nature Publishing Group}
}

@article{hartley2009global,
  title={Global optimization through rotation space search},
  author={Hartley, Richard I and Kahl, Fredrik},
  journal={International Journal of Computer Vision},
  volume={82},
  number={1},
  pages={64--79},
  year={2009},
  publisher={Springer}
}

@inproceedings{wu2018shift,
  title={Shift: A zero flop, zero parameter alternative to spatial convolutions},
  author={Wu, Bichen and Wan, Alvin and Yue, Xiangyu and Jin, Peter and Zhao, Sicheng and Golmant, Noah and Gholaminejad, Amir and Gonzalez, Joseph and Keutzer, Kurt},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={9127--9135},
  year={2018}
}

@article{bommasani2021opportunities,
  title={On the opportunities and risks of foundation models},
  author={Bommasani, Rishi and Hudson, Drew A and Adeli, Ehsan and Altman, Russ and Arora, Simran and von Arx, Sydney and Bernstein, Michael S and Bohg, Jeannette and Bosselut, Antoine and Brunskill, Emma and others},
  journal={arXiv preprint arXiv:2108.07258},
  year={2021}
}

@article{schuhmannlaion,
  title={LAION-5B: An open large-scale dataset for training next generation image-text models},
  author={Schuhmann, Christoph and Beaumont, Romain and Gordon, Cade W and Wightman, Ross and Coombes, Theo and Katta, Aarush and Mullis, Clayton and Schramowski, Patrick and Kundurthy, Srivatsa R and Crowson, Katherine},
  year=2022,
}

@inproceedings{le2013building,
  title={Building high-level features using large scale unsupervised learning},
  author={Le, Quoc V},
  booktitle={2013 IEEE international conference on acoustics, speech and signal processing},
  pages={8595--8598},
  year={2013},
  organization={IEEE}
}

@article{olshausen1996emergence,
  title={Emergence of simple-cell receptive field properties by learning a sparse code for natural images},
  author={Olshausen, Bruno A and Field, David J},
  journal={Nature},
  volume={381},
  number={6583},
  pages={607--609},
  year={1996},
  publisher={Nature Publishing Group}
}

@book{Vapnik95,
  Address =	 {New York},
  Author =	 {V. Vapnik},
  Publisher =	 {Springer},
  Title =	 {The Nature of Statistical Learning Theory},
  Year =	 1995
}

@inproceedings{Novikoff62,
  Author =	 {A.~B.~J.~Novikoff},
  Booktitle =	 {Proceedings of the Symposium on the Mathematical
                  Theory of Automata},
  Organization = {Polytechnic Institute of Brooklyn},
  Pages =	 {615-622},
  Title =	 {On convergence proofs on perceptrons},
  Volume =	 12,
  Year =	 1962
}

@article{ba2016layer,
  title={Layer normalization},
  author={Ba, Jimmy Lei and Kiros, Jamie Ryan and Hinton, Geoffrey E},
  journal={arXiv preprint arXiv:1607.06450},
  year={2016}
}

@article{anil2020scalable,
  title={Scalable second order optimization for deep learning},
  author={Anil, Rohan and Gupta, Vineet and Koren, Tomer and Regan, Kevin and Singer, Yoram},
  journal={arXiv preprint arXiv:2002.09018},
  year={2020}
}

@article{prakash2016neural,
  title={Neural paraphrase generation with stacked residual LSTM networks},
  author={Prakash, Aaditya and Hasan, Sadid A and Lee, Kathy and Datla, Vivek and Qadir, Ashequl and Liu, Joey and Farri, Oladimeji},
  journal={arXiv preprint arXiv:1610.03098},
  year={2016}
}

@article{kim2017residual,
  title={Residual LSTM: Design of a deep recurrent architecture for distant speech recognition},
  author={Kim, Jaeyoung and El-Khamy, Mostafa and Lee, Jungwon},
  journal={arXiv preprint arXiv:1701.03360},
  year={2017}
}

@article{russakovsky2015imagenet,
  title={Imagenet large scale visual recognition challenge},
  author={Russakovsky, Olga and Deng, Jia and Su, Hao and Krause, Jonathan and Satheesh, Sanjeev and Ma, Sean and Huang, Zhiheng and Karpathy, Andrej and Khosla, Aditya and Bernstein, Michael and others},
  journal={International journal of computer vision},
  volume={115},
  number={3},
  pages={211--252},
  year={2015},
  publisher={Springer}
}

@article{forrester2007multi,
  title={Multi-fidelity optimization via surrogate modelling},
  author={Forrester, Alexander IJ and S{\'o}bester, Andr{\'a}s and Keane, Andy J},
  journal={Proceedings of the royal society a: mathematical, physical and engineering sciences},
  volume={463},
  number={2088},
  pages={3251--3269},
  year={2007},
  publisher={The Royal Society London}
}

@inproceedings{dean2012large,
  title={Large scale distributed deep networks},
  author={Dean, Jeffrey and Corrado, Greg S and Monga, Rajat and Chen, Kai and Devin, Matthieu and Le, Quoc V and Mao, Mark Z and Ranzato, Marc'Aurelio and Senior, Andrew and Tucker, Paul and others},
  booktitle={Proceedings of the 25th International Conference on Neural Information Processing Systems-Volume 1},
  pages={1223--1231},
  year={2012}
}

@article{feurer-arxiv22, 
  author = {M. Feurer and B. Letham and F. Hutter and E. Bakshy},
  title = {Practical Transfer Learning for Bayesian Optimization},
  journal = {arXiv:1802.02219 [stat.ML]},
  year = {2022}
}

@article{wistuba-ml18, 
  author = {M. Wistuba and N. Schilling and L. Schmidt-Thieme},
  title = {Scalable gaussian process-based transfer surrogates for hyperparameter optimization},
  journal = {Machine Learning},
  year = {2018}
}

@inproceedings{bardenet-icml13a,
    author    = {R. Bardenet and M. Brendel and B. K{\'e}gl and M. Sebag},
    title     = {Collaborative hyperparameter tuning},
    booktitle = {Proceedings of the 30th International Conference on Machine Learning (ICML'13)},
    year      = {2013},
}

@InProceedings{jenatton-icml17a,
  title	    = {Bayesian {Optimization} with {Tree}-structured {Dependencies}},
  author    = {R. Jenatton and C. Archambeau and J. González and M. Seeger},
  booktitle = {Proceedings of the 34th International Conference on Machine Learning (ICML'17)},
  year      = {2017},

}

@article{li-arxiv18,
 title   = {Massively Parallel Hyperparameter Tuning},
 author  = {L. Li and K. Jamieson and A. Rostamizadeh and K. Gonina and M. Hardt and B. Recht and A. Talwalkar},
 year    = {2018},
 journal = {arXiv:1810.05934 [cs.LG]}
}

@article{bellman-science66,
  title={Dynamic programming},
  author={R. Bellman},
  journal={Science},
  year={1966},
}

@inproceedings{li-iclr17,
 author    = {L. Li and K. Jamieson and G. DeSalvo and A. Rostamizadeh and A. Talwalkar},
 title     = {Hyperband: Bandit-Based Configuration Evaluation for Hyperparameter Optimization},
 booktitle = {International Conference on Learning Representations (ICLR'17)},
 year      = {2017}
}

@inproceedings{karnin-icml13,
  author    = {Z. Karnin and T. Koren and O. Somekh},
  title     = {Almost optimal exploration in multi-armed bandits},
  booktitle = {In Proceedings of the 30th International Conference on Machine Learning (ICML'13)},
  year      = {2013},
}

@inproceedings{jamieson-aistats16,
 author    = {K. Jamieson and A. Talwalkar},
 title     = {Non-stochastic Best Arm Identification and Hyperparameter Optimization},
 booktitle = {Proceedings of the 17th International Conference on Artificial Intelligence and Statistics (AISTATS'16)},
 year      = {2016}
}

@InProceedings{akiba-sigkdd19,
 title     = {{Optuna}: A next-generation hyperparameter optimization framework},
 author    = {T. Akiba and S. Sano and T. Yanase and T. Ohta and M. Koyama},
 booktitle = {Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery \& data mining},
 year      = {2019}
}

@article{liaw-arxiv18,
 author  = {R. Liaw and E. Liang and R. Nishihara and P. Moritz and J. Gonzalez and I. Stoica},
 title   = {{Tune}: A Research Platform for Distributed Model Selection and Training},
 journal = {arXiv:1807.05118 [cs.LG]},
 year    = {2018}
}

@InProceedings{salinas-automl22,
  title     = {Syne Tune: A Library for Large Scale Hyperparameter Tuning and Reproducible Research},
  author    = {D. Salinas and M. Seeger and A. Klein and V. Perrone and M. Wistuba and C. Archambeau},
  booktitle = {First Conference on Automated Machine Learning (Main Track)},
  year      = {2022},
}

@InProceedings{baptista-icml18a,
  title = 	 {{B}ayesian Optimization of Combinatorial Structures},
  author =       {R. Baptista and M. Poloczek},
  booktitle = 	 {Proceedings of the 35th International Conference on Machine Learning},
  year = 	 {2018},
}

@inproceedings{hutter-lion11a,
    author    = {F. Hutter and H. Hoos and K. Leyton-Brown},
    title     = {Sequential Model-Based Optimization for General Algorithm Configuration},
    booktitle = {Proceedings of the Fifth International Conference on Learning and Intelligent Optimization (LION'11)},
    year      = {2011}
}

@inproceedings{franceschi-icml17a,
  title = 	 {Forward and Reverse Gradient-Based Hyperparameter Optimization},
  author = 	 {L. Franceschi and M. Donini and P. Frasconi and M. Pontil},
  booktitle = 	 {Proceedings of the 34th International Conference on Machine Learning (ICML'17)},
  year = 	 {2017},
}

@inproceedings{maclaurin-icml15,
  title = 	 {Gradient-based Hyperparameter Optimization through Reversible Learning},
  author = 	 {D. Maclaurin and D. Duvenaud and R. Adams},
  booktitle = 	 {Proceedings of the 32nd International Conference on Machine Learning (ICML'15)},
  year = 	 {2015}
}

@Book{hutter-book19a,
  editor	= {F. Hutter and L. Kotthoff and J. Vanschoren},
  publisher	= {Springer},
  title		= {Automated Machine Learning: Methods, Systems, Challenges},
  year		= {2019}
}

@article{wistuba-arxiv19,
  author  = {M. Wistuba and A. Rawat and T. Pedapati},
  title   = {A survey on neural architecture search},
  journal = {arXiv:1905.01392 [cs.LG]},
  year    = {2019}
}

@article{elsken-arxiv18a,
  author  = {T. Elsken and J. H. Metzen and F. Hutter},
  title   = {Neural Architecture Search: A Survey},
  journal = {arXiv:1808.05377 [stat.ML]},
  year    = {2018}
}

@incollection{feurer-automlbook18a,
  author    = {M. Feurer and F. Hutter},
  title     = {Hyperparameter Optimization},
  booktitle = {Automatic Machine Learning: Methods, Systems, Challenges},
  year      = {2018},
  publisher = {Springer}
}

@inproceedings{snoek-nips12,
  title       = {Practical {Bayesian} Optimization of Machine Learning Algorithms},
  author      = {Snoek, J. and Larochelle, H. and Adams, R.},
  booktitle   = {Advances in Neural Information Processing Systems 25},
  year        = {2012},
  pages       = {2951--2959}
}

@inproceedings{bergstra-nips11,
  author      = {Bergstra, J. and Bardenet, R. and Bengio, Y. and Kegl, B.},
  booktitle   = {Advances in Neural Information Processing Systems 24},
  year        = {2011},
  pages       = {2546--2554}
}


@article{beltagy2020longformer,
  title={Longformer: The long-document transformer},
  author={Beltagy, Iz and Peters, Matthew E and Cohan, Arman},
  journal={arXiv preprint arXiv:2004.05150},
  year={2020}
}

@article{gulati2020conformer,
  title={Conformer: Convolution-augmented Transformer for Speech Recognition},
  author={Gulati, Anmol and Qin, James and Chiu, Chung-Cheng and Parmar, Niki and Zhang, Yu and Yu, Jiahui and Han, Wei and Wang, Shibo and Zhang, Zhengdong and Wu, Yonghui and others},
  journal={Proc. Interspeech 2020},
  pages={5036--5040},
  year={2020}
}

@article{chen2021decision,
  title={Decision transformer: Reinforcement learning via sequence modeling},
  author={Chen, Lili and Lu, Kevin and Rajeswaran, Aravind and Lee, Kimin and Grover, Aditya and Laskin, Misha and Abbeel, Pieter and Srinivas, Aravind and Mordatch, Igor},
  journal={Advances in neural information processing systems},
  volume={34},
  pages={15084--15097},
  year={2021}
}

@article{dwivedi2020generalization,
  title={A generalization of transformer networks to graphs},
  author={Dwivedi, Vijay Prakash and Bresson, Xavier},
  journal={arXiv preprint arXiv:2012.09699},
  year={2020}
}

@techreport{wolpert1995no,
  title={No free lunch theorems for search},
  author={Wolpert, David H and Macready, William G and others},
  year={1995},
  institution={Technical Report SFI-TR-95-02-010, Santa Fe Institute}
}

@inproceedings{rezende2015variational,
  title={Variational inference with normalizing flows},
  author={Rezende, Danilo and Mohamed, Shakir},
  booktitle={International conference on machine learning},
  pages={1530--1538},
  year={2015},
  organization={PMLR}
}

@inproceedings{sohl2015deep,
  title={Deep unsupervised learning using nonequilibrium thermodynamics},
  author={Sohl-Dickstein, Jascha and Weiss, Eric and Maheswaranathan, Niru and Ganguli, Surya},
  booktitle={International Conference on Machine Learning},
  pages={2256--2265},
  year={2015},
  organization={PMLR}
}

@article{ho2020denoising,
  title={Denoising diffusion probabilistic models},
  author={Ho, Jonathan and Jain, Ajay and Abbeel, Pieter},
  journal={Advances in Neural Information Processing Systems},
  volume={33},
  pages={6840--6851},
  year={2020}
}

@article{song2019generative,
  title={Generative modeling by estimating gradients of the data distribution},
  author={Song, Yang and Ermon, Stefano},
  journal={Advances in Neural Information Processing Systems},
  volume={32},
  year={2019}
}

@article{BellmanDPPaper,
author = {Richard Bellman },
title = {On the Theory of Dynamic Programming},
journal = {Proceedings of the National Academy of Sciences},
volume = {38},
number = {8},
pages = {716-719},
year = {1952},
doi = {10.1073/pnas.38.8.716},
}

@article{BellmanMDP,
 ISSN = {00959057, 19435274},
 URL = {http://www.jstor.org/stable/24900506},
 author = {Richard Bellman},
 journal = {Journal of Mathematics and Mechanics},
 number = {5},
 pages = {679--684},
 publisher = {Indiana University Mathematics Department},
 title = {A Markovian Decision Process},
 urldate = {2022-11-28},
 volume = {6},
 year = {1957}
}

@book{BellmanDPBook,
  isbn={9780486317199},
  publisher = {Dover Publications},
  title = {{Dynamic Programming}},
  year = 1957,
  author = {Richard Bellman },
  series={Dover Books on Computer Science},
}

@article{silver2016mastering,
  title={Mastering the game of Go with deep neural networks and tree search},
  author={Silver, David and Huang, Aja and Maddison, Chris J and Guez, Arthur and Sifre, Laurent and Van Den Driessche, George and Schrittwieser, Julian and Antonoglou, Ioannis and Panneershelvam, Veda and Lanctot, Marc and others},
  journal={nature},
  volume={529},
  number={7587},
  pages={484--489},
  year={2016},
  publisher={Nature Publishing Group}
}

@article{mnih2013playing,
	Author = {Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Graves, Alex and Antonoglou, Ioannis and Wierstra, Daan and Riedmiller, Martin},
	Journal = {arXiv:1312.5602},
	Title = {Playing atari with deep reinforcement learning},
	Year = {2013}
	}

@article{watkinsQlearning1992,
  Author = {Watkins, Christopher J. C. H. and Dayan, Peter},
  Title = {Q-Learning},
  year={1992},
  volume={8},
  Journal={Machine Learning},
  pages={279-292}
}