2024-04-18-chandramoorthy24a.md

title	software	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Score Operator Newton transport	https://doi.org/10.5281/zenodo.10307262	We propose a new approach for sampling and Bayesian computation that uses the score of the target distribution to construct a transport from a given reference distribution to the target. Our approach is an infinite-dimensional Newton method, involving an elliptic PDE, for finding a zero of a “score-residual” operator. We prove sufficient conditions for convergence to a valid transport map. Our Newton iterates can be computed by exploiting fast solvers for elliptic PDEs, resulting in new algorithms for Bayesian inference and other sampling tasks. We identify elementary settings where score-operator Newton transport achieves fast convergence while avoiding mode collapse.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	chandramoorthy24a	0	Score Operator {N}ewton transport	3349	3357	3349-3357	3349	false	Chandramoorthy, Nisha and T Schaefer, Florian and M Marzouk, Youssef	given family Nisha Chandramoorthy given family Florian T Schaefer given family Youssef M Marzouk	2024-04-18		Proceedings of The 27th International Conference on Artificial Intelligence and Statistics	238	inproceedings	date-parts 2024 4 18	https://proceedings.mlr.press/v238/chandramoorthy24a/chandramoorthy24a.pdf