Exportação concluída — 

Parametrizing GP Trees for Better Symbolic Regression Performance through Gradient Descent [Poster]

Detalhes bibliográficos
Autor(a) principal: Pietropolli, Gloria
Data de Publicação: 2023
Outros Autores: Camerota verdù, Federico julian, Manzoni, Luca, Castelli, Mauro
Idioma: eng
Título da fonte: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Texto Completo: http://hdl.handle.net/10362/156122
Resumo: Pietropolli, G., Camerota verdù, F. J., Manzoni, L., & Castelli, M. (2023). Parametrizing GP Trees for Better Symbolic Regression Performance through Gradient Descent [Poster]. In S. Silva, & L. Paquete (Eds.), GECCO '23 Companion: Proceedings of the Companion Conference on Genetic and Evolutionary ComputationJuly 2023 (pp. 619-622). Association for Computing Machinery (ACM). https://doi.org/10.1145/3583133.3590574
id RCAP_21c4bcf5388cda0c1fc0b17d859602f7
oai_identifier_str oai:run.unl.pt:10362/156122
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 Parametrizing GP Trees for Better Symbolic Regression Performance through Gradient Descent [Poster]genetic programminggradient descentlocal searchadammemetic searchSoftwareComputational Theory and MathematicsComputer Science ApplicationsPietropolli, G., Camerota verdù, F. J., Manzoni, L., & Castelli, M. (2023). Parametrizing GP Trees for Better Symbolic Regression Performance through Gradient Descent [Poster]. In S. Silva, & L. Paquete (Eds.), GECCO '23 Companion: Proceedings of the Companion Conference on Genetic and Evolutionary ComputationJuly 2023 (pp. 619-622). Association for Computing Machinery (ACM). https://doi.org/10.1145/3583133.3590574Symbolic regression is a common problem in genetic programming (GP), but the syntactic search carried out by the standard GP algorithm often struggles to tune the learned expressions. On the other hand, gradient-based optimizers can efficiently tune parametric functions by exploring the search space locally. While there is a large amount of research on the combination of evolutionary algorithms and local search (LS) strategies, few of these studies deal with GP. To get the best from both worlds, we propose embedding learnable parameters in GP programs and combining the standard GP evolutionary approach with a gradient-based refinement of the individuals employing the Adam optimizer. We devise two different algorithms that differ in how these parameters are shared in the expression operators and report experimental results performed on a set of standard real-life application datasets. Our findings show that the proposed gradient-based LS approach can be effectively combined with GP to outperform the original algorithm.ACM - Association for Computing MachineryInformation Management Research Center (MagIC) - NOVA Information Management SchoolNOVA Information Management School (NOVA IMS)RUNPietropolli, GloriaCamerota verdù, Federico julianManzoni, LucaCastelli, Mauro2023-08-01T22:13:40Z2023-07-252023-07-25T00:00:00Zconference objectinfo:eu-repo/semantics/publishedVersion4application/pdfhttp://hdl.handle.net/10362/156122eng979-8-4007-0120-7PURE: 67866554https://doi.org/10.1145/3583133.3590574info: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:RCAAP2024-05-22T18:13:33Zoai:run.unl.pt:10362/156122Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T17:44:01.013455Repositórios 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 Parametrizing GP Trees for Better Symbolic Regression Performance through Gradient Descent [Poster]
title Parametrizing GP Trees for Better Symbolic Regression Performance through Gradient Descent [Poster]
spellingShingle Parametrizing GP Trees for Better Symbolic Regression Performance through Gradient Descent [Poster]
Pietropolli, Gloria
genetic programming
gradient descent
local search
adam
memetic search
Software
Computational Theory and Mathematics
Computer Science Applications
title_short Parametrizing GP Trees for Better Symbolic Regression Performance through Gradient Descent [Poster]
title_full Parametrizing GP Trees for Better Symbolic Regression Performance through Gradient Descent [Poster]
title_fullStr Parametrizing GP Trees for Better Symbolic Regression Performance through Gradient Descent [Poster]
title_full_unstemmed Parametrizing GP Trees for Better Symbolic Regression Performance through Gradient Descent [Poster]
title_sort Parametrizing GP Trees for Better Symbolic Regression Performance through Gradient Descent [Poster]
author Pietropolli, Gloria
author_facet Pietropolli, Gloria
Camerota verdù, Federico julian
Manzoni, Luca
Castelli, Mauro
author_role author
author2 Camerota verdù, Federico julian
Manzoni, Luca
Castelli, Mauro
author2_role author
author
author
dc.contributor.none.fl_str_mv Information Management Research Center (MagIC) - NOVA Information Management School
NOVA Information Management School (NOVA IMS)
RUN
dc.contributor.author.fl_str_mv Pietropolli, Gloria
Camerota verdù, Federico julian
Manzoni, Luca
Castelli, Mauro
dc.subject.por.fl_str_mv genetic programming
gradient descent
local search
adam
memetic search
Software
Computational Theory and Mathematics
Computer Science Applications
topic genetic programming
gradient descent
local search
adam
memetic search
Software
Computational Theory and Mathematics
Computer Science Applications
description Pietropolli, G., Camerota verdù, F. J., Manzoni, L., & Castelli, M. (2023). Parametrizing GP Trees for Better Symbolic Regression Performance through Gradient Descent [Poster]. In S. Silva, & L. Paquete (Eds.), GECCO '23 Companion: Proceedings of the Companion Conference on Genetic and Evolutionary ComputationJuly 2023 (pp. 619-622). Association for Computing Machinery (ACM). https://doi.org/10.1145/3583133.3590574
publishDate 2023
dc.date.none.fl_str_mv 2023-08-01T22:13:40Z
2023-07-25
2023-07-25T00:00:00Z
dc.type.driver.fl_str_mv conference object
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/156122
url http://hdl.handle.net/10362/156122
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 979-8-4007-0120-7
PURE: 67866554
https://doi.org/10.1145/3583133.3590574
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 4
application/pdf
dc.publisher.none.fl_str_mv ACM - Association for Computing Machinery
publisher.none.fl_str_mv ACM - Association for Computing Machinery
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_ 1833596924733685760

Registros relacionados