The Polya Tree Sampler: Toward Efficient and Automatic Independent Metropolis-Hastings Proposals

Simple item page
dc.contributor.authorHanson, Timothy E.
dc.contributor.authorMonteiro, Joao V. D.
dc.contributor.authorJara, Alejandro
dc.date.accessioned2024-01-10T12:09:49Z
dc.date.available2024-01-10T12:09:49Z
dc.date.issued2011
dc.description.abstractWe present a simple, efficient, and computationally cheap sampling method for exploring an unnormalized multivariate density on R-d, such as a posterior density, called the Polya tree sampler. The algorithm constructs an independent proposal based on an approximation of the target density. The approximation is built from a set of (initial) support points data that act as parameters for the approximation and the predictive density of a finite multivariate Polya tree. In an initial "warming-up" phase, the support points are iteratively relocated to regions of higher support under the target distribution to minimize the distance between the target distribution and the Polya tree predictive distribution. In the "sampling" phase, samples from the final approximating mixture of finite Polya trees are used as candidates which are accepted with a standard Metropolis Hastings acceptance probability. Several illustrations are presented, including comparisons of the proposed approach to Metropolis-within-Gibbs and delayed rejection adaptive Metropolis algorithm. This article has supplementary material online.
dc.description.funderNIH
dc.description.funderFondecyt
dc.description.funderNATIONAL CANCER INSTITUTE
dc.fechaingreso.objetodigital2024-05-15
dc.format.extent22 páginas
dc.fuente.origenWOS
dc.identifier.doi10.1198/jcgs.2010.09115
dc.identifier.eissn1537-2715
dc.identifier.issn1061-8600
dc.identifier.pubmedidMEDLINE:22135487
dc.identifier.urihttps://doi.org/10.1198/jcgs.2010.09115
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/76525
dc.identifier.wosidWOS:000288580600008
dc.information.autorucMatemática;Jara A ;S/I;127927
dc.issue.numero1
dc.language.isoen
dc.nota.accesocontenido parcial
dc.pagina.final62
dc.pagina.inicio41
dc.publisherAMER STATISTICAL ASSOC
dc.revistaJOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS
dc.rightsacceso restringido
dc.subjectAdaptive Metropolis algorithm
dc.subjectDensity approximation
dc.subjectMetropolis-Hastings algorithm
dc.subjectPolya trees
dc.subjectCHAIN MONTE-CARLO
dc.subjectMIXTURES
dc.subjectDISTRIBUTIONS
dc.subjectGENERATION
dc.subject.ods03 Good Health and Well-being
dc.subject.odspa03 Salud y bienestar
dc.titleThe Polya Tree Sampler: Toward Efficient and Automatic Independent Metropolis-Hastings Proposals
dc.typeartículo
dc.volumen20
sipa.codpersvinculados127927
sipa.indexWOS
sipa.indexScopus
sipa.trazabilidadCarga SIPA;09-01-2024
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2024-05-15. The Polya Tree Sampler - Toward Efficient and Automatic Independent Metropolis-Hastings Proposals.pdf
Size:
2.92 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de revistas