Generalized Maximum Entropy for Supervised Classification

The maximum entropy principle advocates to evaluate events’ probabilities using a distribution that maximizes entropy among those that satisfy certain expectations’ constraints. Such principle can be generalized for arbitrary decision problems where it corresponds to minimax approaches. This paper e...

Descripción completa

Detalles Bibliográficos
Autores: Mazuelas, S., Shen, Y., Pérez, A.
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:España
Institución:Basque Center for Applied Mathematics (BCAM)
Repositorio:BIRD. BCAM's Institutional Repository Data
OAI Identifier:oai:bird.bcamath.org:20.500.11824/1455
Acceso en línea:http://hdl.handle.net/20.500.11824/1455
Access Level:acceso abierto
Palabra clave:Supervised classification
minimax risk classifiers
maximum entropy
generalized entropy
id ES_4d5ca16b728ff6c562bf40ca2f3d4afe
oai_identifier_str oai:bird.bcamath.org:20.500.11824/1455
network_acronym_str ES
network_name_str España
repository_id_str
spelling Generalized Maximum Entropy for Supervised ClassificationMazuelas, S.Shen, Y.Pérez, A.Supervised classificationminimax risk classifiersmaximum entropygeneralized entropyThe maximum entropy principle advocates to evaluate events’ probabilities using a distribution that maximizes entropy among those that satisfy certain expectations’ constraints. Such principle can be generalized for arbitrary decision problems where it corresponds to minimax approaches. This paper establishes a framework for supervised classification based on the generalized maximum entropy principle that leads to minimax risk classifiers (MRCs). We develop learning techniques that determine MRCs for general entropy functions and provide performance guarantees by means of convex optimization. In addition, we describe the relationship of the presented techniques with existing classification methods, and quantify MRCs performance in comparison with the proposed bounds and conventional methods.RYC-2016-19383202220222022info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://hdl.handle.net/20.500.11824/1455reponame:BIRD. BCAM's Institutional Repository Datainstname:Basque Center for Applied Mathematics (BCAM)Ingléshttps://ieeexplore.ieee.org/document/9682746info:eu-repo/grantAgreement/MINECO//SEV-2017-0718info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2019-105058GA-I00info:eu-repo/grantAgreement/Gobierno Vasco/BERC/BERC.2018-2021info:eu-repo/grantAgreement/Gobierno Vasco/ELKARTEK/Reconocimiento-NoComercial-CompartirIgual 3.0 Españahttp://creativecommons.org/licenses/by-nc-sa/3.0/es/info:eu-repo/semantics/openAccessoai:bird.bcamath.org:20.500.11824/14552026-06-19T12:47:47Z
dc.title.none.fl_str_mv Generalized Maximum Entropy for Supervised Classification
title Generalized Maximum Entropy for Supervised Classification
spellingShingle Generalized Maximum Entropy for Supervised Classification
Mazuelas, S.
Supervised classification
minimax risk classifiers
maximum entropy
generalized entropy
title_short Generalized Maximum Entropy for Supervised Classification
title_full Generalized Maximum Entropy for Supervised Classification
title_fullStr Generalized Maximum Entropy for Supervised Classification
title_full_unstemmed Generalized Maximum Entropy for Supervised Classification
title_sort Generalized Maximum Entropy for Supervised Classification
dc.creator.none.fl_str_mv Mazuelas, S.
Shen, Y.
Pérez, A.
author Mazuelas, S.
author_facet Mazuelas, S.
Shen, Y.
Pérez, A.
author_role author
author2 Shen, Y.
Pérez, A.
author2_role author
author
dc.subject.none.fl_str_mv Supervised classification
minimax risk classifiers
maximum entropy
generalized entropy
topic Supervised classification
minimax risk classifiers
maximum entropy
generalized entropy
description The maximum entropy principle advocates to evaluate events’ probabilities using a distribution that maximizes entropy among those that satisfy certain expectations’ constraints. Such principle can be generalized for arbitrary decision problems where it corresponds to minimax approaches. This paper establishes a framework for supervised classification based on the generalized maximum entropy principle that leads to minimax risk classifiers (MRCs). We develop learning techniques that determine MRCs for general entropy functions and provide performance guarantees by means of convex optimization. In addition, we describe the relationship of the presented techniques with existing classification methods, and quantify MRCs performance in comparison with the proposed bounds and conventional methods.
publishDate 2022
dc.date.none.fl_str_mv 2022
2022
2022
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/20.500.11824/1455
url http://hdl.handle.net/20.500.11824/1455
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv https://ieeexplore.ieee.org/document/9682746
info:eu-repo/grantAgreement/MINECO//SEV-2017-0718
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2019-105058GA-I00
info:eu-repo/grantAgreement/Gobierno Vasco/BERC/BERC.2018-2021
info:eu-repo/grantAgreement/Gobierno Vasco/ELKARTEK/
dc.rights.none.fl_str_mv Reconocimiento-NoComercial-CompartirIgual 3.0 España
http://creativecommons.org/licenses/by-nc-sa/3.0/es/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Reconocimiento-NoComercial-CompartirIgual 3.0 España
http://creativecommons.org/licenses/by-nc-sa/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:BIRD. BCAM's Institutional Repository Data
instname:Basque Center for Applied Mathematics (BCAM)
instname_str Basque Center for Applied Mathematics (BCAM)
reponame_str BIRD. BCAM's Institutional Repository Data
collection BIRD. BCAM's Institutional Repository Data
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407686629523456
score 15,300724

Similares en LA Referencia