Pith

open record

sign in
Browse

arxiv: 2508.17545 · v1 · pith:LFZAN2Q5 · submitted 2025-08-24 · stat.ML · cs.LG· math.PR

High-Order Langevin Monte Carlo Algorithms

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:LFZAN2Q5record.jsonopen to challenge →

classification stat.ML cs.LGmath.PR
keywords algorithmscarlolangevinmonteordercdotepsilonfrac
0
0 comments X
read the original abstract

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 $O\left(d^{\frac{1}{R}}/\epsilon^{\frac{1}{2R}}\right)$ 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 $\epsilon$ as $P$ grows. Numerical experiments illustrate the efficiency of our proposed algorithms.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.