Saved in:
Bibliographic Details
Main Authors: Guo, Wei, Tao, Molei, Chen, Yongxin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.16936
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915153470029824
author Guo, Wei
Tao, Molei
Chen, Yongxin
author_facet Guo, Wei
Tao, Molei
Chen, Yongxin
contents We consider the outstanding problem of sampling from an unnormalized density that may be non-log-concave and multimodal. To enhance the performance of simple Markov chain Monte Carlo (MCMC) methods, techniques of annealing type have been widely used. However, quantitative theoretical guarantees of these techniques are under-explored. This study takes a first step toward providing a non-asymptotic analysis of annealed MCMC. Specifically, we establish, for the first time, an oracle complexity of $\widetilde{O}\left(\frac{dβ^2{\cal A}^2}{\varepsilon^6}\right)$ for the simple annealed Langevin Monte Carlo algorithm to achieve $\varepsilon^2$ accuracy in Kullback-Leibler divergence to the target distribution $π\propto{\rm e}^{-V}$ on $\mathbb{R}^d$ with $β$-smooth potential $V$. Here, ${\cal A}$ represents the action of a curve of probability measures interpolating the target distribution $π$ and a readily sampleable distribution.
format Preprint
id arxiv_https___arxiv_org_abs_2407_16936
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling
Guo, Wei
Tao, Molei
Chen, Yongxin
Machine Learning
Statistics Theory
Computation
We consider the outstanding problem of sampling from an unnormalized density that may be non-log-concave and multimodal. To enhance the performance of simple Markov chain Monte Carlo (MCMC) methods, techniques of annealing type have been widely used. However, quantitative theoretical guarantees of these techniques are under-explored. This study takes a first step toward providing a non-asymptotic analysis of annealed MCMC. Specifically, we establish, for the first time, an oracle complexity of $\widetilde{O}\left(\frac{dβ^2{\cal A}^2}{\varepsilon^6}\right)$ for the simple annealed Langevin Monte Carlo algorithm to achieve $\varepsilon^2$ accuracy in Kullback-Leibler divergence to the target distribution $π\propto{\rm e}^{-V}$ on $\mathbb{R}^d$ with $β$-smooth potential $V$. Here, ${\cal A}$ represents the action of a curve of probability measures interpolating the target distribution $π$ and a readily sampleable distribution.
title Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling
topic Machine Learning
Statistics Theory
Computation
url https://arxiv.org/abs/2407.16936