Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates

Autores
Cerino, Franco; Diaz Pace, Jorge Andres; Tassone, Emmanuel Agustin; Tiglio, Manuel; Villegas, Atuel
Año de publicación
2024
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
In a previous work, we introduced, in the context of gravitational wave science, an initial study on an automated domain-decomposition approach for a reduced basis through hp-greedy refinement. The approach constructs local reduced bases of lower dimensionality than global ones, with the same or higher accuracy. These “light” local bases should imply both faster evaluations when predicting new waveforms and faster data analysis, particularly faster statistical inference (the forward and inverse problems, respectively). In this approach, however, we have previously found important dependence on several hyperparameters, which do not appear in a global reduced basis. This naturally leads to the problem of hyperparameter optimization (HPO), which is the subject of this paper. Here, we compare the efficiency of the Bayesian approach against grid and random searches, which are two order of magnitude slower. Then, we tackle the problem of HPO through Bayesian optimization.We find that, for the cases studied here of gravitational waves from the collision of two spinning but non-precessing black holes, for the same accuracy, local hp-greedy reduced bases with HPO have a lower dimensionality of up to 4×, depending on the desired accuracy. This factor should directly translate into a parameter estimation speedup in the context of reduced order quadratures, for instance. Such acceleration might help in the near real-time requirements for electromagnetic counterparts of gravitational waves from compact binary coalescences. The code developed for this project is available open source from public repositories.
Fil: Cerino, Franco. Universidad Nacional de Córdoba; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; Argentina
Fil: Diaz Pace, Jorge Andres. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil. Instituto Superior de Ingeniería del Software. Universidad Nacional del Centro de la Provincia de Buenos Aires. Instituto Superior de Ingeniería del Software; Argentina
Fil: Tassone, Emmanuel Agustin. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Física Enrique Gaviola. Universidad Nacional de Córdoba. Instituto de Física Enrique Gaviola; Argentina
Fil: Tiglio, Manuel. Universidad Nacional de Córdoba; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; Argentina
Fil: Villegas, Atuel. Universidad Nacional de Tucumán; Argentina
Materia
GRAVITATIONAL WAVE SURROGATES
MACHINE LEARNING
REDUCED BASIS
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/260856
Acceder
id CONICETDig_52d64b62d620375e3b9374c641f8ee58
oai_identifier_str oai:ri.conicet.gov.ar:11336/260856
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave SurrogatesCerino, FrancoDiaz Pace, Jorge AndresTassone, Emmanuel AgustinTiglio, ManuelVillegas, AtuelGRAVITATIONAL WAVE SURROGATESMACHINE LEARNINGREDUCED BASIShttps://purl.org/becyt/ford/1.3https://purl.org/becyt/ford/1In a previous work, we introduced, in the context of gravitational wave science, an initial study on an automated domain-decomposition approach for a reduced basis through hp-greedy refinement. The approach constructs local reduced bases of lower dimensionality than global ones, with the same or higher accuracy. These “light” local bases should imply both faster evaluations when predicting new waveforms and faster data analysis, particularly faster statistical inference (the forward and inverse problems, respectively). In this approach, however, we have previously found important dependence on several hyperparameters, which do not appear in a global reduced basis. This naturally leads to the problem of hyperparameter optimization (HPO), which is the subject of this paper. Here, we compare the efficiency of the Bayesian approach against grid and random searches, which are two order of magnitude slower. Then, we tackle the problem of HPO through Bayesian optimization.We find that, for the cases studied here of gravitational waves from the collision of two spinning but non-precessing black holes, for the same accuracy, local hp-greedy reduced bases with HPO have a lower dimensionality of up to 4×, depending on the desired accuracy. This factor should directly translate into a parameter estimation speedup in the context of reduced order quadratures, for instance. Such acceleration might help in the near real-time requirements for electromagnetic counterparts of gravitational waves from compact binary coalescences. The code developed for this project is available open source from public repositories.Fil: Cerino, Franco. Universidad Nacional de Córdoba; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; ArgentinaFil: Diaz Pace, Jorge Andres. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil. Instituto Superior de Ingeniería del Software. Universidad Nacional del Centro de la Provincia de Buenos Aires. Instituto Superior de Ingeniería del Software; ArgentinaFil: Tassone, Emmanuel Agustin. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Física Enrique Gaviola. Universidad Nacional de Córdoba. Instituto de Física Enrique Gaviola; ArgentinaFil: Tiglio, Manuel. Universidad Nacional de Córdoba; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; ArgentinaFil: Villegas, Atuel. Universidad Nacional de Tucumán; ArgentinaMDPI2024-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/260856Cerino, Franco; Diaz Pace, Jorge Andres; Tassone, Emmanuel Agustin; Tiglio, Manuel; Villegas, Atuel; Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates; MDPI; Universe; 10; 1; 1-2024; 1-142218-1997CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://www.mdpi.com/2218-1997/10/1/6info:eu-repo/semantics/altIdentifier/doi/10.3390/universe10010006info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-17T11:10:56Zoai:ri.conicet.gov.ar:11336/260856instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-17 11:10:56.37CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates
title Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates
spellingShingle Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates
Cerino, Franco
GRAVITATIONAL WAVE SURROGATES
MACHINE LEARNING
REDUCED BASIS
title_short Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates
title_full Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates
title_fullStr Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates
title_full_unstemmed Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates
title_sort Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates
dc.creator.none.fl_str_mv Cerino, Franco
Diaz Pace, Jorge Andres
Tassone, Emmanuel Agustin
Tiglio, Manuel
Villegas, Atuel
author Cerino, Franco
author_facet Cerino, Franco
Diaz Pace, Jorge Andres
Tassone, Emmanuel Agustin
Tiglio, Manuel
Villegas, Atuel
author_role author
author2 Diaz Pace, Jorge Andres
Tassone, Emmanuel Agustin
Tiglio, Manuel
Villegas, Atuel
author2_role author
author
author
author
dc.subject.none.fl_str_mv GRAVITATIONAL WAVE SURROGATES
MACHINE LEARNING
REDUCED BASIS
topic GRAVITATIONAL WAVE SURROGATES
MACHINE LEARNING
REDUCED BASIS
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.3
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv In a previous work, we introduced, in the context of gravitational wave science, an initial study on an automated domain-decomposition approach for a reduced basis through hp-greedy refinement. The approach constructs local reduced bases of lower dimensionality than global ones, with the same or higher accuracy. These “light” local bases should imply both faster evaluations when predicting new waveforms and faster data analysis, particularly faster statistical inference (the forward and inverse problems, respectively). In this approach, however, we have previously found important dependence on several hyperparameters, which do not appear in a global reduced basis. This naturally leads to the problem of hyperparameter optimization (HPO), which is the subject of this paper. Here, we compare the efficiency of the Bayesian approach against grid and random searches, which are two order of magnitude slower. Then, we tackle the problem of HPO through Bayesian optimization.We find that, for the cases studied here of gravitational waves from the collision of two spinning but non-precessing black holes, for the same accuracy, local hp-greedy reduced bases with HPO have a lower dimensionality of up to 4×, depending on the desired accuracy. This factor should directly translate into a parameter estimation speedup in the context of reduced order quadratures, for instance. Such acceleration might help in the near real-time requirements for electromagnetic counterparts of gravitational waves from compact binary coalescences. The code developed for this project is available open source from public repositories.
Fil: Cerino, Franco. Universidad Nacional de Córdoba; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; Argentina
Fil: Diaz Pace, Jorge Andres. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil. Instituto Superior de Ingeniería del Software. Universidad Nacional del Centro de la Provincia de Buenos Aires. Instituto Superior de Ingeniería del Software; Argentina
Fil: Tassone, Emmanuel Agustin. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Física Enrique Gaviola. Universidad Nacional de Córdoba. Instituto de Física Enrique Gaviola; Argentina
Fil: Tiglio, Manuel. Universidad Nacional de Córdoba; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; Argentina
Fil: Villegas, Atuel. Universidad Nacional de Tucumán; Argentina
description In a previous work, we introduced, in the context of gravitational wave science, an initial study on an automated domain-decomposition approach for a reduced basis through hp-greedy refinement. The approach constructs local reduced bases of lower dimensionality than global ones, with the same or higher accuracy. These “light” local bases should imply both faster evaluations when predicting new waveforms and faster data analysis, particularly faster statistical inference (the forward and inverse problems, respectively). In this approach, however, we have previously found important dependence on several hyperparameters, which do not appear in a global reduced basis. This naturally leads to the problem of hyperparameter optimization (HPO), which is the subject of this paper. Here, we compare the efficiency of the Bayesian approach against grid and random searches, which are two order of magnitude slower. Then, we tackle the problem of HPO through Bayesian optimization.We find that, for the cases studied here of gravitational waves from the collision of two spinning but non-precessing black holes, for the same accuracy, local hp-greedy reduced bases with HPO have a lower dimensionality of up to 4×, depending on the desired accuracy. This factor should directly translate into a parameter estimation speedup in the context of reduced order quadratures, for instance. Such acceleration might help in the near real-time requirements for electromagnetic counterparts of gravitational waves from compact binary coalescences. The code developed for this project is available open source from public repositories.
publishDate 2024
dc.date.none.fl_str_mv 2024-01
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/260856
Cerino, Franco; Diaz Pace, Jorge Andres; Tassone, Emmanuel Agustin; Tiglio, Manuel; Villegas, Atuel; Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates; MDPI; Universe; 10; 1; 1-2024; 1-14
2218-1997
CONICET Digital
CONICET
url http://hdl.handle.net/11336/260856
identifier_str_mv Cerino, Franco; Diaz Pace, Jorge Andres; Tassone, Emmanuel Agustin; Tiglio, Manuel; Villegas, Atuel; Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates; MDPI; Universe; 10; 1; 1-2024; 1-14
2218-1997
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://www.mdpi.com/2218-1997/10/1/6
info:eu-repo/semantics/altIdentifier/doi/10.3390/universe10010006
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1843606440467496960
score 13.001348

Publicaciones similares