Matches in SemOpenAlex for { <https://semopenalex.org/work/W2742770167> ?p ?o ?g. }
- W2742770167 endingPage "1697" @default.
- W2742770167 startingPage "1684" @default.
- W2742770167 abstract "Despite its long history of success, the EM algorithm has been vulnerable to local entrapment when the posterior/likelihood is multi-modal. This is particularly pronounced in spike-and-slab posterior distributions for Bayesian variable selection. The main thrust of this article is to introduce the particle EM algorithm, a new population-based optimization strategy that harvests multiple modes in search spaces that present many local maxima. Motivated by nonparametric variational Bayes strategies, particle EM achieves this goal by deploying an ensemble of interactive repulsive particles. These particles are geared toward uncharted areas of the posterior, providing a more comprehensive summary of its topography than simple parallel EM deployments. A sequential Monte Carlo variant of particle EM is also proposed that explores a sequence of annealed posteriors by sampling from a set of mutually avoiding particles. Particle EM outputs a deterministic reconstruction of the posterior distribution for approximate fully Bayes inference by capturing its essential modes and mode weights. This reconstruction reflects model selection uncertainty and is supported by asymptotic considerations, which indicate that the requisite number of particles need not be large in the presence of sparsity (when p > n). Supplementary materials for this article are available online." @default.
- W2742770167 created "2017-08-17" @default.
- W2742770167 creator A5091109856 @default.
- W2742770167 date "2018-06-19" @default.
- W2742770167 modified "2023-09-27" @default.
- W2742770167 title "Particle EM for Variable Selection" @default.
- W2742770167 cites W1483307070 @default.
- W2742770167 cites W1580282541 @default.
- W2742770167 cites W1965125844 @default.
- W2742770167 cites W1966543131 @default.
- W2742770167 cites W1969415786 @default.
- W2742770167 cites W1971289666 @default.
- W2742770167 cites W1981299323 @default.
- W2742770167 cites W1982651526 @default.
- W2742770167 cites W2007069447 @default.
- W2742770167 cites W2007463795 @default.
- W2742770167 cites W2011471859 @default.
- W2742770167 cites W2013718670 @default.
- W2742770167 cites W2049633694 @default.
- W2742770167 cites W2054657612 @default.
- W2742770167 cites W2055025635 @default.
- W2742770167 cites W2099170797 @default.
- W2742770167 cites W2100404003 @default.
- W2742770167 cites W2101169975 @default.
- W2742770167 cites W2112141145 @default.
- W2742770167 cites W2120633557 @default.
- W2742770167 cites W2138779671 @default.
- W2742770167 cites W2148178414 @default.
- W2742770167 cites W2168634963 @default.
- W2742770167 cites W2330192890 @default.
- W2742770167 cites W2788365376 @default.
- W2742770167 cites W2963680191 @default.
- W2742770167 doi "https://doi.org/10.1080/01621459.2017.1360778" @default.
- W2742770167 hasPublicationYear "2018" @default.
- W2742770167 type Work @default.
- W2742770167 sameAs 2742770167 @default.
- W2742770167 citedByCount "10" @default.
- W2742770167 countsByYear W27427701672016 @default.
- W2742770167 countsByYear W27427701672017 @default.
- W2742770167 countsByYear W27427701672018 @default.
- W2742770167 countsByYear W27427701672019 @default.
- W2742770167 countsByYear W27427701672020 @default.
- W2742770167 countsByYear W27427701672022 @default.
- W2742770167 countsByYear W27427701672023 @default.
- W2742770167 crossrefType "journal-article" @default.
- W2742770167 hasAuthorship W2742770167A5091109856 @default.
- W2742770167 hasBestOaLocation W27427701672 @default.
- W2742770167 hasConcept C105795698 @default.
- W2742770167 hasConcept C107673813 @default.
- W2742770167 hasConcept C11413529 @default.
- W2742770167 hasConcept C126255220 @default.
- W2742770167 hasConcept C144024400 @default.
- W2742770167 hasConcept C149923435 @default.
- W2742770167 hasConcept C154945302 @default.
- W2742770167 hasConcept C157286648 @default.
- W2742770167 hasConcept C160234255 @default.
- W2742770167 hasConcept C177769412 @default.
- W2742770167 hasConcept C19499675 @default.
- W2742770167 hasConcept C207201462 @default.
- W2742770167 hasConcept C2908647359 @default.
- W2742770167 hasConcept C33923547 @default.
- W2742770167 hasConcept C41008148 @default.
- W2742770167 hasConcept C52421305 @default.
- W2742770167 hasConcept C52740198 @default.
- W2742770167 hasConcept C57830394 @default.
- W2742770167 hasConceptScore W2742770167C105795698 @default.
- W2742770167 hasConceptScore W2742770167C107673813 @default.
- W2742770167 hasConceptScore W2742770167C11413529 @default.
- W2742770167 hasConceptScore W2742770167C126255220 @default.
- W2742770167 hasConceptScore W2742770167C144024400 @default.
- W2742770167 hasConceptScore W2742770167C149923435 @default.
- W2742770167 hasConceptScore W2742770167C154945302 @default.
- W2742770167 hasConceptScore W2742770167C157286648 @default.
- W2742770167 hasConceptScore W2742770167C160234255 @default.
- W2742770167 hasConceptScore W2742770167C177769412 @default.
- W2742770167 hasConceptScore W2742770167C19499675 @default.
- W2742770167 hasConceptScore W2742770167C207201462 @default.
- W2742770167 hasConceptScore W2742770167C2908647359 @default.
- W2742770167 hasConceptScore W2742770167C33923547 @default.
- W2742770167 hasConceptScore W2742770167C41008148 @default.
- W2742770167 hasConceptScore W2742770167C52421305 @default.
- W2742770167 hasConceptScore W2742770167C52740198 @default.
- W2742770167 hasConceptScore W2742770167C57830394 @default.
- W2742770167 hasFunder F4320306076 @default.
- W2742770167 hasIssue "524" @default.
- W2742770167 hasLocation W27427701671 @default.
- W2742770167 hasLocation W27427701672 @default.
- W2742770167 hasOpenAccess W2742770167 @default.
- W2742770167 hasPrimaryLocation W27427701671 @default.
- W2742770167 hasRelatedWork W1591629481 @default.
- W2742770167 hasRelatedWork W2081420412 @default.
- W2742770167 hasRelatedWork W2133205540 @default.
- W2742770167 hasRelatedWork W2138266733 @default.
- W2742770167 hasRelatedWork W2229010591 @default.
- W2742770167 hasRelatedWork W2588557680 @default.
- W2742770167 hasRelatedWork W2949233932 @default.
- W2742770167 hasRelatedWork W3160546271 @default.
- W2742770167 hasRelatedWork W3163707242 @default.