Relative entropy estimate and geometric ergodicity for implicit Langevin Monte Carlo

TL;DR

This paper analyzes the implicit Langevin Monte Carlo method, providing error bounds and ergodicity results under weaker conditions than explicit schemes, with a focus on relative entropy and PDE techniques.

Contribution

It introduces a new analysis of iLMC, establishing error bounds and geometric ergodicity under one-sided Lipschitz conditions, extending the understanding of implicit schemes.

Findings

Error bound in relative entropy for iLMC.

Proved geometric ergodicity under Wasserstein-1 distance.

Extended error bounds to uniform-in-time results.

Abstract

We study the implicit Langevin Monte Carlo (iLMC) method, which simulates the overdamped Langevin equation via an implicit iteration rule. In many applications, iLMC is favored over other explicit schemes such as the (explicit) Langevin Monte Carlo (LMC). LMC may blow up when the drift field $\nabla U$ is not globally Lipschitz, while iLMC has convergence guarantee when the drift is only one-sided Lipschitz. Starting from an adapted continuous-time interpolation, we prove a time-discretization error bound under the relative entropy (or the Kullback-Leibler divergence), where a crucial gradient estimate for the logarithm numerical density is obtained via a sequence of PDE techniques, including Bernstein method. Based on a reflection-type continuous-discrete coupling method, we prove the geometric ergodicity of iLMC under the Wasserstein-1 distance. Moreover, we extend the error bound to a uniform-in-time one by combining the relative entropy error bound and the ergodicity. Our proof technique is universal and can be applied to other implicit or splitting schemes for simulating stochastic differential equations with non-Lipschitz drifts.