Show simple item record

dc.contributor.authorMazuelas, S. 
dc.contributor.authorZanoni, A.
dc.contributor.authorPérez, A. 
dc.date.accessioned2021-02-14T18:02:00Z
dc.date.available2021-02-14T18:02:00Z
dc.date.issued2020-12-01
dc.identifier.issn1049-5258
dc.identifier.urihttp://hdl.handle.net/20.500.11824/1251
dc.description.abstractSupervised classification techniques use training samples to find classification rules with small expected 0-1 loss. Conventional methods achieve efficient learning and out-of-sample generalization by minimizing surrogate losses over specific families of rules. This paper presents minimax risk classifiers (MRCs) that do not rely on a choice of surrogate loss and family of rules. MRCs achieve efficient learning and out-of-sample generalization by minimizing worst-case expected 0-1 loss w.r.t. uncertainty sets that are defined by linear constraints and include the true underlying distribution. In addition, MRCs’ learning stage provides performance guarantees as lower and upper tight bounds for expected 0-1 loss. We also present MRCs’ finite-sample generalization bounds in terms of training size and smallest minimax risk, and show their competitive classification performance w.r.t. state-of-the-art techniques using benchmark datasets.en_US
dc.description.sponsorshipRamon y Cajal Grant RYC-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 classificationen_US
dc.titleMinimax Classification with 0-1 Loss and Performance Guaranteesen_US
dc.typeinfo:eu-repo/semantics/conferenceObjecten_US
dc.relation.publisherversionhttps://papers.nips.cc/paper/2020/hash/02f657d55eaf1c4840ce8d66fcdaf90c-Abstract.htmlen_US
dc.relation.projectIDES/1PE/SEV-2017-0718en_US
dc.relation.projectIDES/1PE/TIN2017-82626-Ren_US
dc.relation.projectIDES/2PE/PID2019-105058GA-I00en_US
dc.relation.projectIDEUS/BERC/BERC.2018-2021en_US
dc.relation.projectIDEUS/ELKARTEKen_US
dc.rights.accessRightsinfo:eu-repo/semantics/openAccessen_US
dc.type.hasVersioninfo:eu-repo/semantics/publishedVersionen_US
dc.journal.titleAdvances in Neural Information Processing Systemsen_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