A data-dependent skeleton estimate and a scale-sensitive dimension for classification
Full item page Simple item page
- dc.contributor.author Horvath, Marta
- dc.contributor.author Lugosi, Gábor
- dc.contributor.other Universitat Pompeu Fabra. Departament d'Economia i Empresa
- dc.date.accessioned 2020-05-25T09:26:42Z
- dc.date.available 2020-05-25T09:26:42Z
- dc.date.issued 1996-12-01
- dc.date.modified 2020-05-25T09:17:01Z
- dc.description.abstract The classical binary classification problem is investigated when it is known in advance that the posterior probability function (or regression function) belongs to some class of functions. We introduce and analyze a method which effectively exploits this knowledge. The method is based on minimizing the empirical risk over a carefully selected ``skeleton'' of the class of regression functions. The skeleton is a covering of the class based on a data--dependent metric, especially fitted for classification. A new scale--sensitive dimension is introduced which is more useful for the studied classification problem than other, previously defined, dimension measures. This fact is demonstrated by performance bounds for the skeleton estimate in terms of the new dimension.
- dc.format.mimetype application/pdf*
- dc.identifier https://econ-papers.upf.edu/ca/paper.php?id=199
- dc.identifier.citation Discrete Applied Mathematics, 86, (1998), pp. 37-61
- dc.identifier.uri http://hdl.handle.net/10230/1073
- dc.language.iso eng
- dc.relation.ispartofseries Economics and Business Working Papers Series; 199
- 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 estimation
- dc.subject.keyword hypothesis testing
- dc.subject.keyword statistical decision theory: operations research
- dc.subject.keyword Statistics, Econometrics and Quantitative Methods
- dc.title A data-dependent skeleton estimate and a scale-sensitive dimension for classification
- dc.type info:eu-repo/semantics/workingPaper