Show simple item record

Free energy Sequential Monte Carlo, application to mixture modelling

hal.structure.identifier
dc.contributor.authorChopin, Nicolas*
hal.structure.identifier
dc.contributor.authorJacob, Pierre E.
HAL ID: 16651
ORCID: 0000-0002-4662-1051		*
dc.date.accessioned2018-01-12T15:46:00Z
dc.date.available2018-01-12T15:46:00Z
dc.date.issued2011
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/17307
dc.language.isoenen
dc.subjectFree energy biasingen
dc.subjectLabel switchingen
dc.subjectMixtureen
dc.subjectSequential Monte Carloen
dc.subjectparticle filteren
dc.subject.ddc519en
dc.titleFree energy Sequential Monte Carlo, application to mixture modellingen
dc.typeCommunication / Conférence
dc.description.abstractenWe introduce a new class of Sequential Monte Carlo (SMC) methods, which we call free energy SMC. This class is inspired by free energy methods, which originate from Physics, and where one samples from a biased distribution such that a given function $\xi(\theta)$ of the state $\theta$ is forced to be uniformly distributed over a given interval. From an initial sequence of distributions $(\pi_t)$ of interest, and a particular choice of $\xi(\theta)$, a free energy SMC sampler computes sequentially a sequence of biased distributions $(\tilde{\pi}_{t})$ with the following properties: (a) the marginal distribution of $\xi(\theta)$ with respect to $\tilde{\pi}_{t}$ is approximatively uniform over a specified interval, and (b) $\tilde{\pi}_{t}$ and $\pi_{t}$ have the same conditional distribution with respect to $\xi$. We apply our methodology to mixture posterior distributions, which are highly multimodal. In the mixture context, forcing certain hyper-parameters to higher values greatly faciliates mode swapping, and makes it possible to recover a symetric output. We illustrate our approach with univariate and bivariate Gaussian mixtures and two real-world datasets.en
dc.relation.ispartoftitleBayesian Statistics 9en
dc.relation.ispartofeditorBernardo, José M.
dc.relation.ispartofeditorBayarri, M.J.
dc.relation.ispartofeditorBerger, James O.
dc.relation.ispartofeditorDawid, A.P.
dc.relation.ispartofeditorHeckermann, David
dc.relation.ispartofeditorSmith, Adrian F. M.
dc.relation.ispartofeditorWest, Mike
dc.relation.ispartofpublnameOxford University Pressen
dc.relation.ispartofpublcityOxforden
dc.relation.ispartofdate2011
dc.subject.ddclabelProbabilités et mathématiques appliquéesen
dc.relation.ispartofisbn9780199694587en
dc.relation.conftitleBayesian Statistics 9en
dc.relation.confdate2011-06
dc.relation.confcityBenidormen
dc.relation.confcountrySpainen
dc.relation.forthcomingnonen
dc.identifier.doi10.1093/acprof:oso/9780199694587.003.0003en
dc.description.ssrncandidatenonen
dc.description.halcandidatenonen
dc.description.readershiprechercheen
dc.description.audienceInternationalen
dc.relation.Isversionofjnlpeerreviewednonen
dc.relation.Isversionofjnlpeerreviewednonen
dc.date.updated2017-12-22T17:16:34Z
hal.author.functionaut
hal.author.functionaut


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record