A simple randomized algorithm for consistent sequential prediction of ergodic time series
Mostra el registre complet Registre parcial de l'ítem
- dc.contributor.author Györfi, Lászlóca
- dc.contributor.author Lugosi, Gáborca
- dc.contributor.author Morvai, Gusztávca
- dc.contributor.other Universitat Pompeu Fabra. Departament d'Economia i Empresa
- dc.date.accessioned 2017-07-26T10:50:29Z
- dc.date.available 2017-07-26T10:50:29Z
- dc.date.issued 1998-04-01
- dc.date.modified 2017-07-23T02:03:34Z
- dc.description.abstract We present a simple randomized procedure for the prediction of a binary sequence. The algorithm uses ideas from recent developments of the theory of the prediction of individual sequences. We show that if the sequence is a realization of a stationary and ergodic random process then the average number of mistakes converges, almost surely, to that of the optimum, given by the Bayes predictor.
- dc.format.mimetype application/pdfca
- dc.identifier https://econ-papers.upf.edu/ca/paper.php?id=282
- dc.identifier.citation IEEE Transactions on Information Theory, 45, (1999), pp. 2642-2650
- dc.identifier.uri http://hdl.handle.net/10230/922
- dc.language.iso eng
- dc.relation.ispartofseries Economics and Business Working Papers Series; 282
- 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 prediction
- dc.subject.keyword ergodic processes
- dc.subject.keyword pattern classification
- dc.subject.keyword Statistics, Econometrics and Quantitative Methods
- dc.title A simple randomized algorithm for consistent sequential prediction of ergodic time seriesca
- dc.type info:eu-repo/semantics/workingPaper