Quadratic Programming Feature Selection

Biblos-e Archivo/Manakin Repository

Show simple item record

dc.contributor.author Rodríguez-Luján, Irene
dc.contributor.author Elkan, Charles
dc.contributor.author Santa Cruz, Carlos
dc.contributor.author Huerta, Ramón
dc.contributor.other UAM. Departamento de Ingeniería Informática es_ES
dc.date.accessioned 2015-02-10T17:09:01Z
dc.date.available 2015-02-10T17:09:01Z
dc.date.issued 2010-01-04
dc.identifier.citation Journal of Machine Learning Research 11 (2010): 1491-1516 en_US
dc.identifier.issn 1533-7928 (online) en_US
dc.identifier.issn 1532-4435 (print) en_US
dc.identifier.uri http://hdl.handle.net/10486/663723
dc.description.abstract Identifying a subset of features that preserves classification accuracy is a problem of growing importance, because of the increasing size and dimensionality of real-world data sets. We propose a new feature selection method, named Quadratic Programming Feature Selection (QPFS), that reduces the task to a quadratic optimization problem. In order to limit the computational complexity of solving the optimization problem, QPFS uses the Nystr¨om method for approximate matrix diagonalization. QPFS is thus capable of dealing with very large data sets, for which the use of other methods is computationally expensive. In experiments with small and medium data sets, the QPFS method leads to classification accuracy similar to that of other successful techniques. For large data sets, QPFS is superior in terms of computational efficiency. en_US
dc.description.sponsorship I.R.-L. is supported by an FPU grant from Universidad Autónoma de Madrid, and partially supported by the Universidad Autónoma de Madrid-IIC Chair. R.H. acknowledges partial support by ONR N00014-07-1-0741 en_US
dc.format.extent 26 pág. es_ES
dc.format.mimetype application/pdf en
dc.language.iso eng en
dc.publisher M I T Press en_US
dc.relation.ispartof Journal of Machine Learning Research en_US
dc.rights © 2010 Irene Rodriguez-Lujan, Ramon Huerta, Charles Elkan and Carlos Santa Cruz en_US
dc.subject.other Feature selection en_US
dc.subject.other Quadratic programming en_US
dc.subject.other Nyström method en_US
dc.subject.other Large data set en_US
dc.subject.other Highdimensional data en_US
dc.title Quadratic Programming Feature Selection en_US
dc.type article en_US
dc.subject.eciencia Informática es_ES
dc.relation.publisherversion http://jmlr.org/papers/volume11/rodriguez-lujan10a/rodriguez-lujan10a.pdf
dc.identifier.publicationfirstpage 1491
dc.identifier.publicationissue 11
dc.identifier.publicationlastpage 1516
dc.type.version info:eu-repo/semantics/publishedVersion en
dc.contributor.group Aprendizaje Automático (ING EPS-001) es_ES
dc.rights.accessRights openAccess en
dc.authorUAM Huerta Rico, Ramón (259903)
dc.authorUAM Santa Cruz Fernández, Carlos (260561)

Files in this item


This item appears in the following Collection(s)

Show simple item record