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

Detalhes bibliográficos
Autor(a) principal: Pereira, Diogo
Data de Publicação: 2024
Outros Autores: Nunes, Cláudia, Rodrigues, Rui
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Texto Completo: http://hdl.handle.net/10362/178751
Resumo: Publisher Copyright: © 2024 The Author(s)
id RCAP_f58b333fa9b3590317a81e4acd7a0cd8
oai_identifier_str oai:run.unl.pt:10362/178751
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling A new algorithm for inference in HMM's with lower span complexityBaum-Welch algorithmExpectation-Maximization algorithmHidden Markov ModelsParallel computationStatistics and ProbabilityComputational MathematicsComputational Theory and MathematicsApplied MathematicsPublisher Copyright: © 2024 The Author(s)The 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.CMA - Centro de Matemática e AplicaçõesDM - Departamento de MatemáticaRUNPereira, DiogoNunes, CláudiaRodrigues, Rui2025-02-10T21:16:22Z2024-072024-07-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10362/178751eng0167-9473PURE: 106515953https://doi.org/10.1016/j.csda.2024.107955info:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2025-02-24T01:41:33Zoai:run.unl.pt:10362/178751Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T20:39:29.975806Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv A new algorithm for inference in HMM's with lower span complexity
title A new algorithm for inference in HMM's with lower span complexity
spellingShingle A new algorithm for inference in HMM's with lower span complexity
Pereira, Diogo
Baum-Welch algorithm
Expectation-Maximization algorithm
Hidden Markov Models
Parallel computation
Statistics and Probability
Computational Mathematics
Computational Theory and Mathematics
Applied Mathematics
title_short A new algorithm for inference in HMM's with lower span complexity
title_full A new algorithm for inference in HMM's with lower span complexity
title_fullStr A new algorithm for inference in HMM's with lower span complexity
title_full_unstemmed A new algorithm for inference in HMM's with lower span complexity
title_sort A new algorithm for inference in HMM's with lower span complexity
author Pereira, Diogo
author_facet Pereira, Diogo
Nunes, Cláudia
Rodrigues, Rui
author_role author
author2 Nunes, Cláudia
Rodrigues, Rui
author2_role author
author
dc.contributor.none.fl_str_mv CMA - Centro de Matemática e Aplicações
DM - Departamento de Matemática
RUN
dc.contributor.author.fl_str_mv Pereira, Diogo
Nunes, Cláudia
Rodrigues, Rui
dc.subject.por.fl_str_mv Baum-Welch algorithm
Expectation-Maximization algorithm
Hidden Markov Models
Parallel computation
Statistics and Probability
Computational Mathematics
Computational Theory and Mathematics
Applied Mathematics
topic Baum-Welch algorithm
Expectation-Maximization algorithm
Hidden Markov Models
Parallel computation
Statistics and Probability
Computational Mathematics
Computational Theory and Mathematics
Applied Mathematics
description Publisher Copyright: © 2024 The Author(s)
publishDate 2024
dc.date.none.fl_str_mv 2024-07
2024-07-01T00:00:00Z
2025-02-10T21:16:22Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/178751
url http://hdl.handle.net/10362/178751
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 0167-9473
PURE: 106515953
https://doi.org/10.1016/j.csda.2024.107955
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833598778395852800

Registros relacionados