liu.seSök publikationer i DiVA
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Divide-and-Conquer With Sequential Monte Carlo
Uppsala University, Sweden.
University of Warwick, England.
Linköpings universitet, Institutionen för systemteknik, Reglerteknik. Linköpings universitet, Tekniska fakulteten.
Intrepid Net Comp, MT USA.
Visa övriga samt affilieringar
2017 (Engelska)Ingår i: Journal of Computational And Graphical Statistics, ISSN 1061-8600, E-ISSN 1537-2715, Vol. 26, nr 2, s. 445-458Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

We propose a novel class of Sequential Monte Carlo (SMC) algorithms, appropriate for inference in probabilistic graphical models. This class of algorithms adopts a divide-and-conquer approach based upon an auxiliary tree-structured decomposition of the model of interest, turning the overall inferential task into a collection of recursively solved subproblems. The proposed method is applicable to a broad class of probabilistic graphical models, including models with loops. Unlike a standard SMC sampler, the proposed divide-and-conquer SMC employs multiple independent populations of weighted particles, which are resampled, merged, and propagated as the method progresses. We illustrate empirically that this approach can outperform standard methods in terms of the accuracy of the posterior expectation and marginal likelihood approximations. Divide-and-conquer SMC also opens up novel parallel implementation options and the possibility of concentrating the computational effort on the most challenging subproblems. We demonstrate its performance on a Markov random field and on a hierarchical logistic regression problem. Supplementary materials including proofs and additional numerical results are available online.

Ort, förlag, år, upplaga, sidor
AMER STATISTICAL ASSOC , 2017. Vol. 26, nr 2, s. 445-458
Nyckelord [en]
Bayesian methods; Graphical models; Hierarchical models; Particle filters
Nationell ämneskategori
Sannolikhetsteori och statistik
Identifikatorer
URN: urn:nbn:se:liu:diva-137624DOI: 10.1080/10618600.2016.1237363ISI: 000400182800020OAI: oai:DiVA.org:liu-137624DiVA, id: diva2:1097342
Anmärkning

Funding Agencies|Swedish research Council [637-2014-466]; Probabilistic modeling of dynamical systems [621-2013-5524]; Linnaeus Center CADICS; Engineering and Physical Sciences Research Council [EP/K021672/2]; Natural Sciences and Engineering Research Council (Canada)

Tillgänglig från: 2017-05-22 Skapad: 2017-05-22 Senast uppdaterad: 2019-08-23

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltext

Person

Lindsten, FredrikAndersson Naesseth, Christian

Sök vidare i DiVA

Av författaren/redaktören
Lindsten, FredrikAndersson Naesseth, Christian
Av organisationen
ReglerteknikTekniska fakulteten
I samma tidskrift
Journal of Computational And Graphical Statistics
Sannolikhetsteori och statistik

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 286 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf