Non-asymptotic bounds for sampling algorithms without log-concavity

TL;DR

This paper develops non-asymptotic $L^2$ convergence bounds for Euler discretisation algorithms used in sampling high-dimensional distributions, replacing the common log-concavity assumption with a weaker condition at infinity.

Contribution

It introduces novel $L^2$ convergence rates under a log-concavity at infinity condition and provides bounds for both standard and randomized drift schemes, including multi-level Monte Carlo methods.

Findings

Established explicit $L^2$ convergence rates in terms of problem parameters.

Derived non-asymptotic bounds for laws of Euler schemes and invariant measures.

Showed variance of randomized drift does not affect weak convergence rate.

Abstract

Discrete time analogues of ergodic stochastic differential equations (SDEs) are one of the most popular and flexible tools for sampling high-dimensional probability measures. Non-asymptotic analysis in the $L^2$ Wasserstein distance of sampling algorithms based on Euler discretisations of SDEs has been recently developed by several authors for log-concave probability distributions. In this work we replace the log-concavity assumption with a log-concavity at infinity condition. We provide novel $L^2$ convergence rates for Euler schemes, expressed explicitly in terms of problem parameters. From there we derive non-asymptotic bounds on the distance between the laws induced by Euler schemes and the invariant laws of SDEs, both for schemes with standard and with randomised (inaccurate) drifts. We also obtain bounds for the hierarchy of discretisation, which enables us to deploy a multi-level Monte Carlo estimator. Our proof relies on a novel construction of a coupling for the Markov chains that can be used to control both the $L^1$ and $L^2$ Wasserstein distances simultaneously. Finally, we provide a weak convergence analysis that covers both the standard and the randomised (inaccurate) drift case. In particular, we reveal that the variance of the randomised drift does not influence the rate of weak convergence of the Euler scheme to the SDE.