Convergence rate of randomized midpoint Langevin Monte Carlo

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Ruinan, Shen, Tian, Su, Zhonggen
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909908016824320
author Li, Ruinan
Shen, Tian
Su, Zhonggen
author_facet Li, Ruinan
Shen, Tian
Su, Zhonggen
contents The randomized midpoint Langevin Monte Carlo (RLMC), introduced by Shen and Lee (2019), is a variant of classical Unadjusted Langevin Algorithm. It was shown in the literature that the RLMC is an efficient algorithm for approximating high-dimensional probability distribution $π$. In this paper, we establish the exponential ergodicity of RLMC with constant step-size. Moreover, we design a dereasing-step size RLMC and provide its convergence rate in terms of a functional class distance.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13093
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Convergence rate of randomized midpoint Langevin Monte Carlo
Li, Ruinan
Shen, Tian
Su, Zhonggen
Statistics Theory
Probability
The randomized midpoint Langevin Monte Carlo (RLMC), introduced by Shen and Lee (2019), is a variant of classical Unadjusted Langevin Algorithm. It was shown in the literature that the RLMC is an efficient algorithm for approximating high-dimensional probability distribution $π$. In this paper, we establish the exponential ergodicity of RLMC with constant step-size. Moreover, we design a dereasing-step size RLMC and provide its convergence rate in terms of a functional class distance.
title Convergence rate of randomized midpoint Langevin Monte Carlo
topic Statistics Theory
Probability
url https://arxiv.org/abs/2511.13093