Recombinative EMCMC algorithms

M.M. Drugan, D. Thierens

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

3 Citations (Scopus)
2 Downloads (Pure)

Abstract

Evolutionary Markov Chain Monte Carlo (EMCMC) is a class of algorithms obtained by merging Markov chain Monte Carlo algorithms with evolutionary computation methods. EMCMC integrates techniques from the EC framework (population, recombination and selection) into the MCMC framework to increase the performance of the standard MCMC algorithms. In this paper, we show how to use recombination operators in EMCMC and how to combine them with other existing MCMC techniques (e.g. mutation and selection). We illustrate these principles by means of an example.

Original languageEnglish
Title of host publicationThe 2005 IEEE Congress on Evolutionary Computation, 2-5 September 2005, Edinburgh, Scotland
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages2024-2031
Number of pages8
ISBN (Print)0780393635
DOIs
Publication statusPublished - 2005
Externally publishedYes
Event2005 IEEE Congress on Evolutionary Computation (CEC 2005) - Edinburgh, Scotland, United Kingdom
Duration: 2 Sep 20055 Sep 2005

Conference

Conference2005 IEEE Congress on Evolutionary Computation (CEC 2005)
CountryUnited Kingdom
CityEdinburgh, Scotland
Period2/09/055/09/05
OtherThe 2005 IEE Congress on Evolutionary Computation (CEC 2005)

Fingerprint Dive into the research topics of 'Recombinative EMCMC algorithms'. Together they form a unique fingerprint.

Cite this