Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible

Daniil Ryabko 1 Boris Ryabko 2
1 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : The problem of prediction consists in forecasting the conditional distribution of the next outcome given the past. Assume that the source generating the data is such that there is a stationary predictor whose error converges to zero (in a certain sense). The question is whether there is a universal predictor for all such sources, that is, a predictor whose error goes to zero if any of the sources that have this property is chosen to generate the data. This question is answered in the negative, contrasting a number of previously established positive results concerning related but smaller sets of processes.
Type de document :
Communication dans un congrès
International Symposium on Information Theory, Jun 2015, Hong Kong, Hong Kong SAR China. IEEE, pp.1204-1206
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01165876
Contributeur : Daniil Ryabko <>
Soumis le : mercredi 24 juin 2015 - 10:58:31
Dernière modification le : mardi 3 juillet 2018 - 11:44:21
Document(s) archivé(s) le : mardi 25 avril 2017 - 18:24:06

Fichier

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

Identifiants

  • HAL Id : hal-01165876, version 1

Collections

Citation

Daniil Ryabko, Boris Ryabko. Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible. International Symposium on Information Theory, Jun 2015, Hong Kong, Hong Kong SAR China. IEEE, pp.1204-1206. 〈hal-01165876〉

Partager

Métriques

Consultations de la notice

186

Téléchargements de fichiers

57