Complexity and global rates of trust-region methods based on probabilistic models
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10316/89439 https://doi.org/10.1093/imanum/drx043 |
Resumo: | Trust-region algorithms have been proved to globally converge with probability 1 when the accuracy of the trust-region models is imposed with a certain probability conditioning on the iteration history. In this article, we study the complexity of such methods, providing global rates and worst-case complexity bounds on the number of iterations (with overwhelmingly high probability), for both first- and second-order measures of optimality. Such results are essentially the same as the ones known for trust-region methods based on deterministic models. The derivation of the global rates and worst-case complexity bounds follows closely from a study of direct search methods based on the companion notion of probabilistic descent. |
id |
RCAP_4a89bc3f29522755f937a35b4607dc1b |
---|---|
oai_identifier_str |
oai:estudogeral.uc.pt:10316/89439 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Complexity and global rates of trust-region methods based on probabilistic modelsTrust-region methods; Worst-case complexity; Probabilistic models.Trust-region algorithms have been proved to globally converge with probability 1 when the accuracy of the trust-region models is imposed with a certain probability conditioning on the iteration history. In this article, we study the complexity of such methods, providing global rates and worst-case complexity bounds on the number of iterations (with overwhelmingly high probability), for both first- and second-order measures of optimality. Such results are essentially the same as the ones known for trust-region methods based on deterministic models. The derivation of the global rates and worst-case complexity bounds follows closely from a study of direct search methods based on the companion notion of probabilistic descent.Oxford University Press - Institute of Mathematics and its Applications2018-07info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/10316/89439http://hdl.handle.net/10316/89439https://doi.org/10.1093/imanum/drx043enghttps://academic.oup.com/imajna/article/38/3/1579/4084726Gratton, SergeRoyer, Clément WVicente, Luís NunesZhang, Zaikuninfo: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:RCAAP2022-05-25T03:06:07Zoai:estudogeral.uc.pt:10316/89439Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T21:09:45.214390Repositório 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 |
Complexity and global rates of trust-region methods based on probabilistic models |
title |
Complexity and global rates of trust-region methods based on probabilistic models |
spellingShingle |
Complexity and global rates of trust-region methods based on probabilistic models Gratton, Serge Trust-region methods; Worst-case complexity; Probabilistic models. |
title_short |
Complexity and global rates of trust-region methods based on probabilistic models |
title_full |
Complexity and global rates of trust-region methods based on probabilistic models |
title_fullStr |
Complexity and global rates of trust-region methods based on probabilistic models |
title_full_unstemmed |
Complexity and global rates of trust-region methods based on probabilistic models |
title_sort |
Complexity and global rates of trust-region methods based on probabilistic models |
author |
Gratton, Serge |
author_facet |
Gratton, Serge Royer, Clément W Vicente, Luís Nunes Zhang, Zaikun |
author_role |
author |
author2 |
Royer, Clément W Vicente, Luís Nunes Zhang, Zaikun |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Gratton, Serge Royer, Clément W Vicente, Luís Nunes Zhang, Zaikun |
dc.subject.por.fl_str_mv |
Trust-region methods; Worst-case complexity; Probabilistic models. |
topic |
Trust-region methods; Worst-case complexity; Probabilistic models. |
description |
Trust-region algorithms have been proved to globally converge with probability 1 when the accuracy of the trust-region models is imposed with a certain probability conditioning on the iteration history. In this article, we study the complexity of such methods, providing global rates and worst-case complexity bounds on the number of iterations (with overwhelmingly high probability), for both first- and second-order measures of optimality. Such results are essentially the same as the ones known for trust-region methods based on deterministic models. The derivation of the global rates and worst-case complexity bounds follows closely from a study of direct search methods based on the companion notion of probabilistic descent. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-07 |
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/10316/89439 http://hdl.handle.net/10316/89439 https://doi.org/10.1093/imanum/drx043 |
url |
http://hdl.handle.net/10316/89439 https://doi.org/10.1093/imanum/drx043 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
https://academic.oup.com/imajna/article/38/3/1579/4084726 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Oxford University Press - Institute of Mathematics and its Applications |
publisher.none.fl_str_mv |
Oxford University Press - Institute of Mathematics and its Applications |
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_ |
1799133992883060736 |