2022-06-28-chen22c.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
Improved analysis for a proximal algorithm for sampling	We study the proximal sampler of Lee, Shen, and Tian (2021) and obtain new convergence guarantees under weaker assumptions than strong log-concavity: namely, our results hold for (1) weakly log-concave targets, and (2) targets satisfying isoperimetric assumptions which allow for non-log-concavity. We demonstrate our results by obtaining new state-of-the-art sampling guarantees for several classes of target distributions. We also strengthen the connection between the proximal sampler and the proximal method in optimization by interpreting the former as an entropically regularized Wasserstein gradient flow and the latter as the limit of one.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	chen22c	0	Improved analysis for a proximal algorithm for sampling	2984	3014	2984-3014	2984	false	Chen, Yongxin and Chewi, Sinho and Salim, Adil and Wibisono, Andre	given family Yongxin Chen given family Sinho Chewi given family Adil Salim given family Andre Wibisono	2022-06-28		Proceedings of Thirty Fifth Conference on Learning Theory	178	inproceedings	date-parts 2022 6 28	https://proceedings.mlr.press/v178/chen22c/chen22c.pdf