Optimal friction matrix for underdamped Langevin sampling - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year : 2021

Optimal friction matrix for underdamped Langevin sampling

Abstract

A systematic procedure for optimising the friction coefficient in underdamped Langevin dynamics as a sampling tool is given by taking the gradient of the associated asymptotic variance with respect to friction. We give an expression for this gradient in terms of the solution to an appropriate Poisson equation and show that it can be approximated by short simulations of the associated first variation/tangent process under concavity assumptions on the log density. Our algorithm is applied to the estimation of posterior means in Bayesian inference problems and reduced variance is demonstrated when compared to the original underdamped and overdamped Langevin dynamics in both full and stochastic gradient cases.
Fichier principal
Vignette du fichier
Algo.pdf (1.02 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03455809 , version 1 (29-11-2021)

Identifiers

Cite

Martin Chak, Nikolas Kantas, Tony Lelièvre, Grigorios A Pavliotis. Optimal friction matrix for underdamped Langevin sampling. 2021. ⟨hal-03455809⟩
171 View
241 Download

Altmetric

Share

Gmail Facebook X LinkedIn More