On variance stabilisation in population Monte Carlo by double Rao-Blackwellisation
dc.contributor.author | Robert, Christian P. | |
dc.contributor.author | Marin, Jean-Michel
HAL ID: 9121 ORCID: 0000-0001-7451-9719 | |
dc.contributor.author | Iacobucci, Alessandra
HAL ID: 739701 ORCID: 0000-0003-4025-3195 | |
dc.date.accessioned | 2009-07-07T09:54:01Z | |
dc.date.available | 2009-07-07T09:54:01Z | |
dc.date.issued | 2010 | |
dc.identifier.uri | https://basepub.dauphine.fr/handle/123456789/872 | |
dc.language.iso | en | en |
dc.subject | Importance sampling mixture | en |
dc.subject | Adaptive Monte Carlo | en |
dc.subject | Population Monte Carlo | en |
dc.subject | Multimodality | en |
dc.subject | Mixture of distributions | en |
dc.subject | Random walk | en |
dc.subject.ddc | 519 | en |
dc.subject.classificationjel | C15 | |
dc.title | On variance stabilisation in population Monte Carlo by double Rao-Blackwellisation | en |
dc.type | Article accepté pour publication ou publié | |
dc.contributor.editoruniversityother | INRIA – Université Paris Sud - Paris XI;France | |
dc.contributor.editoruniversityother | INSEE;France | |
dc.description.abstracten | Population Monte Carlo has been introduced as a sequential importance sampling technique to overcome poor fit of the importance function. In this paper, we compare the performances of the original Population Monte Carlo algorithm with a modified version that eliminates the influence of the transition particle via a double Rao-Blackwellisation. This modification is shown to improve the exploration of the modes through an large simulation experiment on posterior distributions of mean mixtures of distributions. | en |
dc.relation.isversionofjnlname | Computational Statistics and Data Analysis | |
dc.relation.isversionofjnlvol | 54 | |
dc.relation.isversionofjnlissue | 3 | |
dc.relation.isversionofjnldate | 2010-03 | |
dc.relation.isversionofjnlpages | 698-710 | |
dc.relation.isversionofdoi | http://dx.doi.org/10.1016/j.csda.2008.09.020 | |
dc.identifier.urlsite | http://hal.inria.fr/inria-00260141/en/ | en |
dc.description.sponsorshipprivate | non | en |
dc.relation.isversionofjnlpublisher | Elsevier | |
dc.subject.ddclabel | Probabilités et mathématiques appliquées | en |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |