2024-04-18-ananthakrishnan24a.md

title	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
Delegating Data Collection in Decentralized Machine Learning	Motivated by the emergence of decentralized machine learning (ML) ecosystems, we study the delegation of data collection. Taking the field of contract theory as our starting point, we design optimal and near-optimal contracts that deal with two fundamental information asymmetries that arise in decentralized ML: uncertainty in the assessment of model quality and uncertainty regarding the optimal performance of any model. We show that a principal can cope with such asymmetry via simple linear contracts that achieve $1-1/\epsilon$ fraction of the optimal utility. To address the lack of a priori knowledge regarding the optimal performance, we give a convex program that can adaptively and efficiently compute the optimal contract. We also analyze the optimal utility and linear contracts for the more complex setting of multiple interactions.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	ananthakrishnan24a	0	Delegating Data Collection in Decentralized Machine Learning	478	486	478-486	478	false	Ananthakrishnan, Nivasini and Bates, Stephen and Jordan, Michael and Haghtalab, Nika	given family Nivasini Ananthakrishnan given family Stephen Bates given family Michael Jordan given family Nika Haghtalab	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/ananthakrishnan24a/ananthakrishnan24a.pdf