Parallel and interacting Markov chains Monte Carlo method

Fabien Campillo 1 Vivien Rossi 2
1 ASPI - Applications of interacting particle systems to statistics
UR1 - Université de Rennes 1, Inria Rennes – Bretagne Atlantique , CNRS - Centre National de la Recherche Scientifique : UMR6074
Abstract : In many situations it is important to be able to propose $N$ independent realizations of a given distribution law. We propose a strategy for making $N$ parallel Monte Carlo Markov Chains (MCMC) interact in order to get an approximation of an independent $N$-sample of a given target law. In this method each individual chain proposes candidates for all other chains. We prove that the set of interacting chains is itself a MCMC method for the product of $N$ target measures. Compared to independent parallel chains this method is more time consuming, but we show through concrete examples that it possesses many advantages: it can speed up convergence toward the target law as well as handle the multi-modal case.
Type de document :
[Research Report] RR-6008, INRIA. 2006
Liste complète des métadonnées
Contributeur : Rapport de Recherche Inria <>
Soumis le : jeudi 2 novembre 2006 - 12:01:06
Dernière modification le : lundi 19 février 2018 - 09:52:01
Document(s) archivé(s) le : lundi 20 septembre 2010 - 16:42:20





Fabien Campillo, Vivien Rossi. Parallel and interacting Markov chains Monte Carlo method. [Research Report] RR-6008, INRIA. 2006. 〈inria-00103871v2〉



Consultations de la notice


Téléchargements de fichiers