A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1

Abstract
Stein Variational Gradient Descent (SVGD) is an algorithm for sampling from a target density which is known up to a multiplicative constant. Although SVGD is a popular algorithm in practice, its theoretical study is limited to a few recent works. We study the convergence of SVGD in the population limit, (i.e., with an infinite number of particles) to sample from a non-logconcave target distribution satisfying Talagrand's inequality T1. We first establish the convergence of the algorithm. Then, we establish a dimension-dependent complexity bound in terms of the Kernelized Stein Discrepancy (KSD). Unlike existing works, we do not assume that the KSD is bounded along the trajectory of the algorithm. Our approach relies on interpreting SVGD as a gradient descent over a space of probability measures.

Publisher
MLResearchPress

Conference/Event Name
39th International Conference on Machine Learning (ICML)

arXiv
2106.03076

Additional Links
https://proceedings.mlr.press/v162/salim22a.htmlhttps://arxiv.org/pdf/2106.03076.pdf

Permanent link to this record

Version History

Now showing 1 - 2 of 2
VersionDateSummary
2*
2023-03-16 13:59:35
Published as conference paper
2021-06-09 06:22:41
* Selected version