Show simple item record

dc.contributor.authorDouc, Randal
dc.contributor.authorGuillin, Arnaud
dc.contributor.authorMarin, Jean-Michel
dc.contributor.authorRobert, Christian P.
dc.date.accessioned2011-05-30T12:05:21Z
dc.date.available2011-05-30T12:05:21Z
dc.date.issued2007
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/6362
dc.language.isoenen
dc.subjectBayesian statisticsen
dc.subjectLLNen
dc.subjectKullback divergenceen
dc.subjectMCMC algorithmen
dc.subjectpopulation Monte Carloen
dc.subjectproposal distributionen
dc.subjectRao–Blackwellizationen
dc.subject.ddc519en
dc.titleConvergence of adaptive mixtures of importance sampling schemesen
dc.typeArticle accepté pour publication ou publié
dc.description.abstractenIn the design of efficient simulation algorithms, one is often beset with a poor choice of proposal distributions. Although the performance of a given simulation kernel can clarify a posteriori how adequate this kernel is for the problem at hand, a permanent on-line modification of kernels causes concerns about the validity of the resulting algorithm. While the issue is most often intractable for MCMC algorithms, the equivalent version for importance sampling algorithms can be validated quite precisely. We derive sufficient convergence conditions for adaptive mixtures of population Monte Carlo algorithms and show that Rao–Blackwellized versions asymptotically achieve an optimum in terms of a Kullback divergence criterion, while more rudimentary versions do not benefit from repeated updating.en
dc.relation.isversionofjnlnameAnnals of Statistics
dc.relation.isversionofjnlvol35en
dc.relation.isversionofjnlissue1en
dc.relation.isversionofjnldate2007
dc.relation.isversionofjnlpages420-448en
dc.relation.isversionofdoihttp://dx.doi.org/10.1214/009053606000001154en
dc.description.sponsorshipprivateouien
dc.relation.isversionofjnlpublisherInstitute of Mathematical Statisticsen
dc.subject.ddclabelProbabilités et mathématiques appliquéesen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record