A Caltech Library Service

Spectral gaps for a Metropolis–Hastings algorithm in infinite dimensions

Hairer, Martin and Stuart, Andrew M. and Vollmer, Sebastian (2014) Spectral gaps for a Metropolis–Hastings algorithm in infinite dimensions. Annals of Applied Probability, 24 (6). pp. 2455-2490. ISSN 1050-5164.

[img] PDF - Published Version
See Usage Policy.

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


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.

Item Type:Article
Related URLs:
URLURL TypeDescription Paper
Additional Information:© Institute of Mathematical Statistics, 2014. Received December 2011; revised February 2013. [MR is] supported by EPSRC, the Royal Society, and the Leverhulme Trust. [AMS is] Supported by EPSRC and ERC. [SJV is] Supported by ERC.
Funding AgencyGrant Number
Leverhulme TrustUNSPECIFIED
Subject Keywords:asserstein spectral gaps, L^2 -spectral gaps, Markov chain Monte Carlo in infinite dimensions, weak Harris theorem, random walk Metropolis
Other Numbering System:
Other Numbering System NameOther Numbering System ID
Andrew StuartJ112
Issue or Number:6
Classification Code:MSC2010 subject classifications. 65C40, 60B10, 60J05, 60J22
Record Number:CaltechAUTHORS:20160719-144104557
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:69116
Deposited By: Linda Taddeo
Deposited On:19 Jul 2016 23:35
Last Modified:03 Oct 2019 10:19

Repository Staff Only: item control page