Some sufficient conditions on an arbitrary class of stochastic processes for the existence of a predictor.

Daniil Ryabko 1
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Abstract : We consider the problem of sequence prediction in a probabilistic setting. Let there be given a class C of stochastic processes (probability measures on the set of one-way infinite sequences). We are interested in the question of what are the conditions on C under which there exists a predictor (also a stochastic process) for which the predicted probabilities converge to the correct ones if any of the processes in C is chosen to generate the data. We find some sufficient conditions on C under which such a predictor exists. Some of the conditions are asymptotic in nature, while others are based on the local (truncated to first observations) behaviour of the processes. The conditions lead to constructions of the predictors. In some cases we also obtain rates of convergence that are optimal up to an additive logarithmic term.
Type de document :
Communication dans un congrès
Freund, Y.; Györfi, L.; Turán, G.; Zeugmann, Th. 19th International Conference on Algorithmic Learning Theory, ALT 2008, Oct 2008, Budapest, Hungary. Springer, 5254, pp.169-182, 2008, Lecture Notes in Artificial Intelligence. 〈http://link.springer.com/chapter/10.1007/978-3-540-87987-9_17〉. 〈10.1007/978-3-540-87987-9_17〉
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00347706
Contributeur : Daniil Ryabko <>
Soumis le : mardi 16 décembre 2008 - 15:29:36
Dernière modification le : jeudi 11 janvier 2018 - 06:22:13
Document(s) archivé(s) le : jeudi 11 octobre 2012 - 13:55:15

Fichier

pq_.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Daniil Ryabko. Some sufficient conditions on an arbitrary class of stochastic processes for the existence of a predictor.. Freund, Y.; Györfi, L.; Turán, G.; Zeugmann, Th. 19th International Conference on Algorithmic Learning Theory, ALT 2008, Oct 2008, Budapest, Hungary. Springer, 5254, pp.169-182, 2008, Lecture Notes in Artificial Intelligence. 〈http://link.springer.com/chapter/10.1007/978-3-540-87987-9_17〉. 〈10.1007/978-3-540-87987-9_17〉. 〈inria-00347706〉

Partager

Métriques

Consultations de la notice

371

Téléchargements de fichiers

142