Exploring parameter spaces with artificial intelligence and machine learning black-box optimisation algorithms
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | https://hdl.handle.net/1822/83192 |
Resumo: | Constraining Beyond the Standard Model theories usually involves scanning highly multi-dimensional parameter spaces and check observable predictions against experimental bounds and theoretical constraints. Such task is often timely and computationally expensive, especially when the model is severely constrained and thus leading to very low random sampling efficiency. In this work we tackled this challenge using Artificial Intelligence and Machine Learning search algorithms used for Black-Box optimisation problems. Using the cMSSM and the pMSSM parameter spaces, we consider both the Higgs mass and the Dark Matter Relic Density constraints to study their sampling efficiency and parameter space coverage. We find our methodology to produce orders of magnitude improvement of sampling efficiency whilst reasonably covering the parameter space. |
id |
RCAP_453e245f1361b0798bd09c738dc880d7 |
---|---|
oai_identifier_str |
oai:repositorium.sdum.uminho.pt:1822/83192 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Exploring parameter spaces with artificial intelligence and machine learning black-box optimisation algorithmsCiências Naturais::Ciências FísicasScience & TechnologyConstraining Beyond the Standard Model theories usually involves scanning highly multi-dimensional parameter spaces and check observable predictions against experimental bounds and theoretical constraints. Such task is often timely and computationally expensive, especially when the model is severely constrained and thus leading to very low random sampling efficiency. In this work we tackled this challenge using Artificial Intelligence and Machine Learning search algorithms used for Black-Box optimisation problems. Using the cMSSM and the pMSSM parameter spaces, we consider both the Higgs mass and the Dark Matter Relic Density constraints to study their sampling efficiency and parameter space coverage. We find our methodology to produce orders of magnitude improvement of sampling efficiency whilst reasonably covering the parameter space.We thank José Santiago Pérez and Jorge Romão for the careful reading of the paper draft and for the useful discussions. This work is supported by FCT - Fundação para a Ciência e a Tecnologia, I.P. under project CERN/FIS-PAR/0024/2019. FAS is also supported by FCT under the research grant with reference UI/BD/153105/2022. The computational work was partially done using the resources made available by RNCA and INCD under project CPCA/A1/401197/2021info:eu-repo/semantics/publishedVersionAmerican Physical SocietyUniversidade do MinhoSouza, Fernando Abreu deRomão, Miguel CrispimCastro, Nuno FilipeNikjoo, MehravehPorod, Werner2023-02-062023-02-06T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/1822/83192eng2470-00102470-002910.1103/PhysRevD.107.035004https://journals.aps.org/prd/pdf/10.1103/PhysRevD.107.035004info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-07-21T12:52:46Zoai:repositorium.sdum.uminho.pt:1822/83192Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T19:51:58.618756Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Exploring parameter spaces with artificial intelligence and machine learning black-box optimisation algorithms |
title |
Exploring parameter spaces with artificial intelligence and machine learning black-box optimisation algorithms |
spellingShingle |
Exploring parameter spaces with artificial intelligence and machine learning black-box optimisation algorithms Souza, Fernando Abreu de Ciências Naturais::Ciências Físicas Science & Technology |
title_short |
Exploring parameter spaces with artificial intelligence and machine learning black-box optimisation algorithms |
title_full |
Exploring parameter spaces with artificial intelligence and machine learning black-box optimisation algorithms |
title_fullStr |
Exploring parameter spaces with artificial intelligence and machine learning black-box optimisation algorithms |
title_full_unstemmed |
Exploring parameter spaces with artificial intelligence and machine learning black-box optimisation algorithms |
title_sort |
Exploring parameter spaces with artificial intelligence and machine learning black-box optimisation algorithms |
author |
Souza, Fernando Abreu de |
author_facet |
Souza, Fernando Abreu de Romão, Miguel Crispim Castro, Nuno Filipe Nikjoo, Mehraveh Porod, Werner |
author_role |
author |
author2 |
Romão, Miguel Crispim Castro, Nuno Filipe Nikjoo, Mehraveh Porod, Werner |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade do Minho |
dc.contributor.author.fl_str_mv |
Souza, Fernando Abreu de Romão, Miguel Crispim Castro, Nuno Filipe Nikjoo, Mehraveh Porod, Werner |
dc.subject.por.fl_str_mv |
Ciências Naturais::Ciências Físicas Science & Technology |
topic |
Ciências Naturais::Ciências Físicas Science & Technology |
description |
Constraining Beyond the Standard Model theories usually involves scanning highly multi-dimensional parameter spaces and check observable predictions against experimental bounds and theoretical constraints. Such task is often timely and computationally expensive, especially when the model is severely constrained and thus leading to very low random sampling efficiency. In this work we tackled this challenge using Artificial Intelligence and Machine Learning search algorithms used for Black-Box optimisation problems. Using the cMSSM and the pMSSM parameter spaces, we consider both the Higgs mass and the Dark Matter Relic Density constraints to study their sampling efficiency and parameter space coverage. We find our methodology to produce orders of magnitude improvement of sampling efficiency whilst reasonably covering the parameter space. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-02-06 2023-02-06T00:00:00Z |
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 |
https://hdl.handle.net/1822/83192 |
url |
https://hdl.handle.net/1822/83192 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
2470-0010 2470-0029 10.1103/PhysRevD.107.035004 https://journals.aps.org/prd/pdf/10.1103/PhysRevD.107.035004 |
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.publisher.none.fl_str_mv |
American Physical Society |
publisher.none.fl_str_mv |
American Physical Society |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799133109951660032 |