Non-asymptotic analysis of Langevin-type Monte Carlo algorithms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Nakakita, Shogo
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914695133265920
author Nakakita, Shogo
author_facet Nakakita, Shogo
contents We study Langevin-type algorithms for sampling from Gibbs distributions such that the potentials are dissipative and their weak gradients have finite moduli of continuity not necessarily convergent to zero. Our main result is a non-asymptotic upper bound of the 2-Wasserstein distance between a Gibbs distribution and the law of general Langevin-type algorithms based on the Liptser--Shiryaev theory and Poincaré inequalities. We apply this bound to show that the Langevin Monte Carlo algorithm can approximate Gibbs distributions with arbitrary accuracy if the potentials are dissipative and their gradients are uniformly continuous. We also propose Langevin-type algorithms with spherical smoothing for distributions whose potentials are not convex or continuously differentiable.
format Preprint
id arxiv_https___arxiv_org_abs_2303_12407
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Non-asymptotic analysis of Langevin-type Monte Carlo algorithms
Nakakita, Shogo
Statistics Theory
Probability
Machine Learning
65C05
We study Langevin-type algorithms for sampling from Gibbs distributions such that the potentials are dissipative and their weak gradients have finite moduli of continuity not necessarily convergent to zero. Our main result is a non-asymptotic upper bound of the 2-Wasserstein distance between a Gibbs distribution and the law of general Langevin-type algorithms based on the Liptser--Shiryaev theory and Poincaré inequalities. We apply this bound to show that the Langevin Monte Carlo algorithm can approximate Gibbs distributions with arbitrary accuracy if the potentials are dissipative and their gradients are uniformly continuous. We also propose Langevin-type algorithms with spherical smoothing for distributions whose potentials are not convex or continuously differentiable.
title Non-asymptotic analysis of Langevin-type Monte Carlo algorithms
topic Statistics Theory
Probability
Machine Learning
65C05
url https://arxiv.org/abs/2303.12407