Show simple item record

dc.contributor.authorMazuelas, S. 
dc.contributor.authorShen, Y.
dc.contributor.authorPérez, A. 
dc.date.accessioned2022-03-20T18:34:45Z
dc.date.available2022-03-20T18:34:45Z
dc.date.issued2022-04
dc.identifier.issn0018-9448
dc.identifier.urihttp://hdl.handle.net/20.500.11824/1455
dc.description.abstractThe 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.en_US
dc.description.sponsorshipRYC-2016-19383en_US
dc.formatapplication/pdfen_US
dc.language.isoengen_US
dc.rightsReconocimiento-NoComercial-CompartirIgual 3.0 Españaen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/es/en_US
dc.subjectSupervised classificationen_US
dc.subjectminimax risk classifiersen_US
dc.subjectmaximum entropyen_US
dc.subjectgeneralized entropyen_US
dc.titleGeneralized Maximum Entropy for Supervised Classificationen_US
dc.typeinfo:eu-repo/semantics/articleen_US
dc.identifier.doi10.1109/TIT.2022.3143764en_US
dc.relation.publisherversionhttps://ieeexplore.ieee.org/document/9682746en_US
dc.relation.projectIDinfo:eu-repo/grantAgreement/MINECO//SEV-2017-0718en_US
dc.relation.projectIDinfo:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2019-105058GA-I00en_US
dc.relation.projectIDinfo:eu-repo/grantAgreement/Gobierno Vasco/BERC/BERC.2018-2021en_US
dc.relation.projectIDinfo:eu-repo/grantAgreement/Gobierno Vasco/ELKARTEKen_US
dc.rights.accessRightsinfo:eu-repo/semantics/openAccessen_US
dc.type.hasVersioninfo:eu-repo/semantics/publishedVersionen_US
dc.journal.titleIEEE Transactions on Information Theoryen_US
dc.volume.number68en_US
dc.issue.number4en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Reconocimiento-NoComercial-CompartirIgual 3.0 España
Except where otherwise noted, this item's license is described as Reconocimiento-NoComercial-CompartirIgual 3.0 España