Translator Disclaimer
December 2014 Spectral gaps for a Metropolis–Hastings algorithm in infinite dimensions
Martin Hairer, Andrew M. Stuart, Sebastian J. Vollmer
Ann. Appl. Probab. 24(6): 2455-2490 (December 2014). DOI: 10.1214/13-AAP982

Abstract

We study the problem of sampling high and infinite dimensional target measures arising in applications such as conditioned diffusions and inverse problems. We focus on those that arise from approximating measures on Hilbert spaces defined via a density with respect to a Gaussian reference measure. We consider the Metropolis–Hastings algorithm that adds an accept–reject mechanism to a Markov chain proposal in order to make the chain reversible with respect to the target measure. We focus on cases where the proposal is either a Gaussian random walk (RWM) with covariance equal to that of the reference measure or an Ornstein–Uhlenbeck proposal (pCN) for which the reference measure is invariant.

Previous results in terms of scaling and diffusion limits suggested that the pCN has a convergence rate that is independent of the dimension while the RWM method has undesirable dimension-dependent behaviour. We confirm this claim by exhibiting a dimension-independent Wasserstein spectral gap for pCN algorithm for a large class of target measures. In our setting this Wasserstein spectral gap implies an $L^{2}$-spectral gap. We use both spectral gaps to show that the ergodic average satisfies a strong law of large numbers, the central limit theorem and nonasymptotic bounds on the mean square error, all dimension independent. In contrast we show that the spectral gap of the RWM algorithm applied to the reference measures degenerates as the dimension tends to infinity.

Citation

Download Citation

Martin Hairer. Andrew M. Stuart. Sebastian J. Vollmer. "Spectral gaps for a Metropolis–Hastings algorithm in infinite dimensions." Ann. Appl. Probab. 24 (6) 2455 - 2490, December 2014. https://doi.org/10.1214/13-AAP982

Information

Published: December 2014
First available in Project Euclid: 26 August 2014

zbMATH: 1307.65002
MathSciNet: MR3262508
Digital Object Identifier: 10.1214/13-AAP982

Subjects:
Primary: 60B10, 60J05, 60J22, 65C40

Rights: Copyright © 2014 Institute of Mathematical Statistics

JOURNAL ARTICLE
36 PAGES


SHARE
Vol.24 • No. 6 • December 2014
Back to Top