Projected Langevin Monte Carlo algorithms in non-convex and super-linear setting

Pang, Chenxu and Wang, Xiaojie and Wu, Yue (2023) Projected Langevin Monte Carlo algorithms in non-convex and super-linear setting. Other. arXiv.org, Ithaca, NY. (https://doi.org/10.48550/arXiv.2312.17077)

[thumbnail of Pang-etal-arXiv-2023-Projected-Langevin-Monte-Carlo-algorithms]
Preview
 Text. Filename: Pang-etal-arXiv-2023-Projected-Langevin-Monte-Carlo-algorithms.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (418kB)| Preview

Abstract

It is of significant interest in many applications to sample from a high-dimensional target distribution π with the density π(dx)∝e−U(x)(dx), based on the temporal discretization of the Langevin stochastic differential equations (SDEs). In this paper, we propose an explicit projected Langevin Monte Carlo (PLMC) algorithm with non-convex potential U and super-linear gradient of U and investigate the non-asymptotic analysis of its sampling error in total variation distance. Equipped with time-independent regularity estimates for the corresponding Kolmogorov equation, we derive the non-asymptotic bounds on the total variation distance between the target distribution of the Langevin SDEs and the law induced by the PLMC scheme with order O(h| ln h|). Moreover, for a given precision ϵ, the smallest number of iterations of the classical Langevin Monte Carlo (LMC) scheme with the non-convex potential U and the globally Lipshitz gradient of U can be guaranteed by order O(d3/2ϵ⋅ln(dϵ)⋅ln(1ϵ)). Numerical experiments are provided to confirm the theoretical findings.

CORE (COnnecting REpositories)