Salvato in:
Dettagli Bibliografici
Autori principali: Lim, Keunwoo, Tao, Molei
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2312.07817
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929403053735936
author Lim, Keunwoo
Tao, Molei
author_facet Lim, Keunwoo
Tao, Molei
contents We consider the convergence of kinetic Langevin dynamics to its ergodic invariant measure, which is Gibbs distribution. Instead of the standard setup where the friction coefficient is a constant scalar, we investigate position-dependent friction coefficient and the possible accelerated convergence it enables. We show that by choosing this coefficient matrix to be $2\sqrt{\text{Hess}V}$, convergence is accelerated in the sense that no constant scalar friction coefficient can lead to faster convergence for a large subset of (nonlinear) strongly-convex potential $V$'s. The speed of convergence is quantified in terms of chi-square divergence from the target distribution, and proved using a Lyapunov approach, based on viewing sampling as optimization in the infinite dimensional space of probability distributions.
format Preprint
id arxiv_https___arxiv_org_abs_2312_07817
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Appropriate State-Dependent Friction Coefficient Accelerates Kinetic Langevin Dynamics
Lim, Keunwoo
Tao, Molei
Probability
We consider the convergence of kinetic Langevin dynamics to its ergodic invariant measure, which is Gibbs distribution. Instead of the standard setup where the friction coefficient is a constant scalar, we investigate position-dependent friction coefficient and the possible accelerated convergence it enables. We show that by choosing this coefficient matrix to be $2\sqrt{\text{Hess}V}$, convergence is accelerated in the sense that no constant scalar friction coefficient can lead to faster convergence for a large subset of (nonlinear) strongly-convex potential $V$'s. The speed of convergence is quantified in terms of chi-square divergence from the target distribution, and proved using a Lyapunov approach, based on viewing sampling as optimization in the infinite dimensional space of probability distributions.
title Appropriate State-Dependent Friction Coefficient Accelerates Kinetic Langevin Dynamics
topic Probability
url https://arxiv.org/abs/2312.07817