Model selection and error estimation
Mostra el registre complet Registre parcial de l'ítem
- dc.contributor.author Bartlett, Peterca
- dc.contributor.author Boucheron, Stéphaneca
- dc.contributor.author Lugosi, Gáborca
- dc.contributor.other Universitat Pompeu Fabra. Departament d'Economia i Empresa
- dc.date.accessioned 2017-07-26T12:07:55Z
- dc.date.available 2017-07-26T12:07:55Z
- dc.date.issued 2000-10-01
- dc.date.modified 2017-07-23T02:05:46Z
- dc.description.abstract We study model selection strategies based on penalized empirical loss minimization. We point out a tight relationship between error estimation and data-based complexity penalization: any good error estimate may be converted into a data-based penalty function and the performance of the estimate is governed by the quality of the error estimate. We consider several penalty functions, involving error estimates on independent test data, empirical {\sc vc} dimension, empirical {\sc vc} entropy, and margin-based quantities. We also consider the maximal difference between the error on the first half of the training data and the second half, and the expected maximal discrepancy, a closely related capacity estimate that can be calculated by Monte Carlo integration. Maximal discrepancy penalty functions are appealing for pattern classification problems, since their computation is equivalent to empirical risk minimization over the training data with some labels flipped.
- dc.format.mimetype application/pdfca
- dc.identifier https://econ-papers.upf.edu/ca/paper.php?id=508
- dc.identifier.citation Machine Learning. vol.48, pp. 85-113, 2002
- dc.identifier.uri http://hdl.handle.net/10230/1148
- dc.language.iso eng
- dc.relation.ispartofseries Economics and Business Working Papers Series; 508
- dc.rights L'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons
- dc.rights.accessRights info:eu-repo/semantics/openAccess
- dc.rights.uri http://creativecommons.org/licenses/by-nc-nd/3.0/es/
- dc.subject.keyword complexity regularization
- dc.subject.keyword model selection
- dc.subject.keyword error estimation
- dc.subject.keyword concentration of measure
- dc.subject.keyword Statistics, Econometrics and Quantitative Methods
- dc.title Model selection and error estimationca
- dc.type info:eu-repo/semantics/workingPaper