Open Access
Translator Disclaimer
August 2015 Optimal scaling for the transient phase of the random walk Metropolis algorithm: The mean-field limit
Benjamin Jourdain, Tony Lelièvre, Błażej Miasojedow
Ann. Appl. Probab. 25(4): 2263-2300 (August 2015). DOI: 10.1214/14-AAP1048

Abstract

We consider the random walk Metropolis algorithm on $\mathbb{R}^{n}$ with Gaussian proposals, and when the target probability measure is the $n$-fold product of a one-dimensional law. In the limit $n\to\infty$, it is well known (see [ Ann. Appl. Probab. 7 (1997) 110–120]) that, when the variance of the proposal scales inversely proportional to the dimension $n$ whereas time is accelerated by the factor $n$, a diffusive limit is obtained for each component of the Markov chain if this chain starts at equilibrium. This paper extends this result when the initial distribution is not the target probability measure. Remarking that the interaction between the components of the chain due to the common acceptance/rejection of the proposed moves is of mean-field type, we obtain a propagation of chaos result under the same scaling as in the stationary case. This proves that, in terms of the dimension $n$, the same scaling holds for the transient phase of the Metropolis–Hastings algorithm as near stationarity. The diffusive and mean-field limit of each component is a diffusion process nonlinear in the sense of McKean. This opens the route to new investigations of the optimal choice for the variance of the proposal distribution in order to accelerate convergence to equilibrium (see [Optimal scaling for the transient phase of Metropolis–Hastings algorithms: The longtime behavior Bernoulli (2014) To appear]).

Citation

Download Citation

Benjamin Jourdain. Tony Lelièvre. Błażej Miasojedow. "Optimal scaling for the transient phase of the random walk Metropolis algorithm: The mean-field limit." Ann. Appl. Probab. 25 (4) 2263 - 2300, August 2015. https://doi.org/10.1214/14-AAP1048

Information

Received: 1 October 2012; Revised: 1 December 2013; Published: August 2015
First available in Project Euclid: 21 May 2015

zbMATH: 1329.60262
MathSciNet: MR3349007
Digital Object Identifier: 10.1214/14-AAP1048

Subjects:
Primary: 60F17 , 60G09 , 60J22 , 65C05 , 65C40

Keywords: diffusion limits , Optimal scaling , propagation of chaos , Random walk Metropolis

Rights: Copyright © 2015 Institute of Mathematical Statistics

JOURNAL ARTICLE
38 PAGES


SHARE
Vol.25 • No. 4 • August 2015
Back to Top