High-Order Langevin Monte Carlo Algorithms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dang, Thanh, Gurbuzbalaban, Mert, Islam, Mohammad Rafiqul, Yao, Nian, Zhu, Lingjiong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915460955504640
author Dang, Thanh
Gurbuzbalaban, Mert
Islam, Mohammad Rafiqul
Yao, Nian
Zhu, Lingjiong
author_facet Dang, Thanh
Gurbuzbalaban, Mert
Islam, Mohammad Rafiqul
Yao, Nian
Zhu, Lingjiong
contents Langevin algorithms are popular Markov chain Monte Carlo (MCMC) methods for large-scale sampling problems that often arise in data science. We propose Monte Carlo algorithms based on the discretizations of $P$-th order Langevin dynamics for any $P\geq 3$. Our design of $P$-th order Langevin Monte Carlo (LMC) algorithms is by combining splitting and accurate integration methods. We obtain Wasserstein convergence guarantees for sampling from distributions with log-concave and smooth densities. Specifically, the mixing time of the $P$-th order LMC algorithm scales as $O\left(d^{\frac{1}{R}}/ε^{\frac{1}{2R}}\right)$ for $R=4\cdot 1_{\{ P=3\}}+ (2P-1)\cdot 1_{\{ P\geq 4\}}$, which has a better dependence on the dimension $d$ and the accuracy level $ε$ as $P$ grows. Numerical experiments illustrate the efficiency of our proposed algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17545
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle High-Order Langevin Monte Carlo Algorithms
Dang, Thanh
Gurbuzbalaban, Mert
Islam, Mohammad Rafiqul
Yao, Nian
Zhu, Lingjiong
Machine Learning
Probability
Langevin algorithms are popular Markov chain Monte Carlo (MCMC) methods for large-scale sampling problems that often arise in data science. We propose Monte Carlo algorithms based on the discretizations of $P$-th order Langevin dynamics for any $P\geq 3$. Our design of $P$-th order Langevin Monte Carlo (LMC) algorithms is by combining splitting and accurate integration methods. We obtain Wasserstein convergence guarantees for sampling from distributions with log-concave and smooth densities. Specifically, the mixing time of the $P$-th order LMC algorithm scales as $O\left(d^{\frac{1}{R}}/ε^{\frac{1}{2R}}\right)$ for $R=4\cdot 1_{\{ P=3\}}+ (2P-1)\cdot 1_{\{ P\geq 4\}}$, which has a better dependence on the dimension $d$ and the accuracy level $ε$ as $P$ grows. Numerical experiments illustrate the efficiency of our proposed algorithms.
title High-Order Langevin Monte Carlo Algorithms
topic Machine Learning
Probability
url https://arxiv.org/abs/2508.17545