Evolutionary Markov chain Monte Carlo

M.M. Drugan, D. Thierens

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

11 Citations (Scopus)

Abstract

Markov chain Monte Carlo (MCMC) is a popular class of algorithms to sample from a complex distribution. A key issue in the design of MCMC algorithms is to improve the proposal mechanism and the mixing behaviour. This has led some authors to propose the use of a population of MCMC chains, while others go even further by integrating techniques from evolutionary computation (EC) into the MCMC framework. This merging of MCMC and EC leads to a class of algorithms, we call Evolutionary Markov Chain Monte Carlo (EMCMC). In this paper we first survey existing EMCMC algorithms and categorise them in two classes: family-competitive EMCMC and population-driven EMCMC. Next, we introduce, the Elitist Coupled Acceptance rule and the Fitness Ordered Tempering algorithm.
Original languageEnglish
Title of host publicationArtificial Evolution
Subtitle of host publication6th International Conference, Evolution Artificielle, EA 2003, Marseilles, France, October 27-30, 2003, Revised Selected Papers
EditorsP. Liardet, P. Collet, C. Fonlupt, E. Lutton, M. Schoenauer
Place of PublicationBerlin
PublisherSpringer
Pages63-76
Number of pages14
ISBN (Print)978-3-540-21523-3
DOIs
Publication statusPublished - 2004
Externally publishedYes

Publication series

NameLNCS
Volume2936

Keywords

  • algorithms

Fingerprint

Dive into the research topics of 'Evolutionary Markov chain Monte Carlo'. Together they form a unique fingerprint.

Cite this