Analysis of Langevin midpoint methods using an anticipative Girsanov theorem

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Zhang, Matthew S.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911061227077632
author Zhang, Matthew S.
author_facet Zhang, Matthew S.
contents We introduce a new method for analyzing midpoint discretizations of stochastic differential equations (SDEs), which are frequently used in Markov chain Monte Carlo (MCMC) methods for sampling from a target measure $π\propto \exp(-V)$. Borrowing techniques from Malliavin calculus, we compute estimates for the Radon-Nikodym derivative for processes on $L^2([0, T); \mathbb{R}^d)$ which may anticipate the Brownian motion, in the sense that they may not be adapted to the filtration at the same time. Applying these to various popular midpoint discretizations, we are able to improve the regularity and cross-regularity results in the literature on sampling methods. We also obtain a query complexity bound of $\widetilde{O}(\frac{κ^{5/4} d^{1/4}}{\varepsilon^{1/2}})$ for obtaining a $\varepsilon^2$-accurate sample in $\mathsf{KL}$ divergence, under log-concavity and strong smoothness assumptions for $\nabla^2 V$.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12791
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Analysis of Langevin midpoint methods using an anticipative Girsanov theorem
Zhang, Matthew S.
Numerical Analysis
Data Structures and Algorithms
Probability
Statistics Theory
We introduce a new method for analyzing midpoint discretizations of stochastic differential equations (SDEs), which are frequently used in Markov chain Monte Carlo (MCMC) methods for sampling from a target measure $π\propto \exp(-V)$. Borrowing techniques from Malliavin calculus, we compute estimates for the Radon-Nikodym derivative for processes on $L^2([0, T); \mathbb{R}^d)$ which may anticipate the Brownian motion, in the sense that they may not be adapted to the filtration at the same time. Applying these to various popular midpoint discretizations, we are able to improve the regularity and cross-regularity results in the literature on sampling methods. We also obtain a query complexity bound of $\widetilde{O}(\frac{κ^{5/4} d^{1/4}}{\varepsilon^{1/2}})$ for obtaining a $\varepsilon^2$-accurate sample in $\mathsf{KL}$ divergence, under log-concavity and strong smoothness assumptions for $\nabla^2 V$.
title Analysis of Langevin midpoint methods using an anticipative Girsanov theorem
topic Numerical Analysis
Data Structures and Algorithms
Probability
Statistics Theory
url https://arxiv.org/abs/2507.12791