Improved analysis for a proximal algorithm for sampling
From MaRDI portal
Abstract: 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 proximal sampler as an entropically regularized Wasserstein proximal method, and the proximal point method as the limit of the proximal sampler with vanishing noise.
This page was built for publication: Improved analysis for a proximal algorithm for sampling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6391000)
