Non-asymptotic bounds for sampling algorithms without log-concavity
This work addresses the theoretical analysis of sampling algorithms for high-dimensional probability measures in machine learning and statistics, providing more general convergence guarantees under relaxed assumptions, though it appears incremental by extending existing results to a broader class of distributions.
The authors tackled the problem of analyzing non-asymptotic convergence rates for Euler discretization schemes in sampling algorithms, replacing the standard log-concavity assumption with a weaker log-concavity at infinity condition, and derived explicit convergence rates in L^2 Wasserstein distance, including bounds for schemes with randomized drifts and multi-level Monte Carlo estimators.
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.