Geometric ergodicity of SGLD via reflection coupling
Probability
2024-08-27 v2 Machine Learning
Machine Learning
Abstract
We consider the geometric ergodicity of the Stochastic Gradient Langevin Dynamics (SGLD) algorithm under nonconvexity settings. Via the technique of reflection coupling, we prove the Wasserstein contraction of SGLD when the target distribution is log-concave only outside some compact set. The time discretization and the minibatch in SGLD introduce several difficulties when applying the reflection coupling, which are addressed by a series of careful estimates of conditional expectations. As a direct corollary, the SGLD with constant step size has an invariant distribution and we are able to obtain its geometric ergodicity in terms of distance. The generalization to non-gradient drifts is also included.
Cite
@article{arxiv.2301.06769,
title = {Geometric ergodicity of SGLD via reflection coupling},
author = {Lei Li and Jian-Guo Liu and Yuliang Wang},
journal= {arXiv preprint arXiv:2301.06769},
year = {2024}
}