Sequence prediction in realizable and non-realizable cases

Daniil Ryabko 1
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal, Inria Lille - Nord Europe
Abstract : A sequence $x_1,\dots,x_n,\dots$ of discrete-valued observations is generated according to some unknown probabilistic law (measure) $\mu$. After observing each outcome, it is required to give the conditional probabilities of the next observation. The realizable case is when the measure $\mu$ belongs to an arbitrary but known class $C$ of process measures. The non-realizable case is when $\mu$ is completely arbitrary, but the prediction performance is measured with respect to a given set $C$ of process measures. We are interested in the relations between these problems and between their solutions, as well as in characterizing the cases when a solution exists, and finding these solutions. We show that if the quality of prediction is measured by total variation distance, then these problems coincide, while if it is measured by expected average KL divergence, then they are different. For some of the formalizations we also show that when a solution exists, it can be obtained as a Bayes mixture over a countable subset of $C$. As an illustration to the general results obtained, we show that a solution to the non-realizable case of the sequence prediction problem exists for the set of all finite-memory processes, but does not exist for the set of all stationary processes.
Type de document :
Communication dans un congrès
Conference on Learning Theory, 2010, Haifa, Israel. pp.119-131, 2010, COLT
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00440669
Contributeur : Daniil Ryabko <>
Soumis le : lundi 20 juin 2011 - 12:17:07
Dernière modification le : jeudi 11 janvier 2018 - 01:49:33
Document(s) archivé(s) le : dimanche 4 décembre 2016 - 23:06:16

Fichiers

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

Identifiants

  • HAL Id : inria-00440669, version 3
  • ARXIV : 1005.5603

Collections

Citation

Daniil Ryabko. Sequence prediction in realizable and non-realizable cases. Conference on Learning Theory, 2010, Haifa, Israel. pp.119-131, 2010, COLT. 〈inria-00440669v3〉

Partager

Métriques

Consultations de la notice

203

Téléchargements de fichiers

138