Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited

Abstract

We revisit the problem of sampling from a target distribution that has a smooth strongly log-concave density everywhere in ${\mathbb{R}}^p$. In this context, if no additional density information is available, the randomized midpoint discretization for the kinetic Langevin diffusion is known to be the most scalable method in high dimensions with large condition numbers. Our main result is a nonasymptotic and easy to compute upper bound on the Wasserstein-2 error of this method. To provide a more thorough explanation of our method for establishing the computable upper bound, we conduct an analysis of the midpoint discretization for the vanilla Langevin process. This analysis helps to clarify the underlying principles and provides valuable insights that we use to establish an improved upper bound for the kinetic Langevin process with the midpoint discretization. Furthermore, by applying these techniques we establish new guarantees for the kinetic Langevin process with Euler discretization, which have a better dependence on the condition number than existing upper bounds.

References in corpus (8)

• What Are Bayesian Neural Network Posteriors Really Like?
• Underdamped Langevin MCMC: A non-asymptotic analysis
• On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness
• Exponential ergodicity of mirror-Langevin diffusions
• Analysis of Langevin Monte Carlo from Poincaré to Log-Sobolev
• Improved Discretization Analysis for Underdamped Langevin Monte Carlo
• Towards a Theory of Non-Log-Concave Sampling: First-Order Stationarity Guarantees for Langevin Monte Carlo
• Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincaré Inequality