Logo do repositório
 
Publicação

A new algorithm for inference in HMM's with lower span complexity

2024-07Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorPereira, Diogo
dc.contributor.authorNunes, Cláudia
dc.contributor.authorRodrigues, Rui
dc.contributor.institutionCMA - Centro de Matemática e Aplicações
dc.contributor.institutionDM - Departamento de Matemática
dc.contributor.pblElsevier Science B.V., Inc
dc.date.accessioned2025-02-10T21:16:22Z
dc.date.available2025-02-10T21:16:22Z
dc.date.issued2024-07
dc.descriptionPublisher Copyright: © 2024 The Author(s)
dc.description.abstractThe maximum likelihood problem for Hidden Markov Models is usually numerically solved by the Baum-Welch algorithm, which uses the Expectation-Maximization algorithm to find the estimates of the parameters. This algorithm has a recursion depth equal to the data sample size and cannot be computed in parallel, which limits the use of modern GPUs to speed up computation time. A new algorithm is proposed that provides the same estimates as the Baum-Welch algorithm, requiring about the same number of iterations, but is designed in such a way that it can be parallelized. As a consequence, it leads to a significant reduction in the computation time. This reduction is illustrated by means of numerical examples, where we consider simulated data as well as real datasets.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent1189986
dc.identifier.doi10.1016/j.csda.2024.107955
dc.identifier.issn0167-9473
dc.identifier.otherPURE: 106515953
dc.identifier.otherPURE UUID: 57277d4d-92fb-401f-bbcb-3eaf08ea1d73
dc.identifier.otherScopus: 85188454757
dc.identifier.urihttp://hdl.handle.net/10362/178751
dc.identifier.urlhttps://www.scopus.com/pages/publications/85188454757
dc.language.isoeng
dc.peerreviewedyes
dc.relationinfo:eu-repo/grantAgreement/FCT/Concurso de avaliação no âmbito do Programa Plurianual de Financiamento de Unidades de I&D (2017%2F2018) - Financiamento Base/UIDB%2F04621%2F2020/PT
dc.relationinfo:eu-repo/grantAgreement/FCT/OE/2020.04832.BD/PT
dc.relationDeep Learning Applications to Optimization Problems in Finance
dc.relationCenter for Mathematics and Applications
dc.subjectBaum-Welch algorithm
dc.subjectExpectation-Maximization algorithm
dc.subjectHidden Markov Models
dc.subjectParallel computation
dc.subjectStatistics and Probability
dc.subjectComputational Mathematics
dc.subjectComputational Theory and Mathematics
dc.subjectApplied Mathematics
dc.titleA new algorithm for inference in HMM's with lower span complexityen
dc.typejournal article
degois.publication.titleComputational Statistics and Data Analysis
degois.publication.volume195
dspace.entity.typePublication
oaire.awardNumberUIDB/04621/2020
oaire.awardNumber2020.04832.BD
oaire.awardNumberUIDB/00297/2020
oaire.awardTitleDeep Learning Applications to Optimization Problems in Finance
oaire.awardTitleCenter for Mathematics and Applications
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/Concurso de avaliação no âmbito do Programa Plurianual de Financiamento de Unidades de I&D (2017%2F2018) - Financiamento Base/UIDB%2F04621%2F2020/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/OE/2020.04832.BD/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00297%2F2020/PT
oaire.fundingStreamConcurso de avaliação no âmbito do Programa Plurianual de Financiamento de Unidades de I&D (2017/2018) - Financiamento Base
oaire.fundingStreamOE
oaire.fundingStream6817 - DCRRNI ID
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccess
relation.isProjectOfPublicatione4cbbd97-920e-4bc8-ab1d-bc58191c496f
relation.isProjectOfPublicationfc2362f4-92a6-4649-bb38-8ae40a901e4f
relation.isProjectOfPublicationd00ae22f-ec2b-47b2-935e-60cb44493cc6
relation.isProjectOfPublication.latestForDiscoveryfc2362f4-92a6-4649-bb38-8ae40a901e4f

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
1-s2.0-S0167947324000392-main.pdf
Tamanho:
1.13 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

Home collection (FCT)