Universality of Bayesian mixture predictors

Daniil Ryabko 1
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 is that of sequential probability forecasting for finite-valued time series. The data is generated by an unknown probability distribution over the space of all one-way infinite sequences. It is known that this measure belongs to a given set C, but the latter is completely arbitrary (uncountably infinite, without any structure given). The performance is measured with asymptotic average log loss. In this work it is shown that the minimax asymptotic performance is always attainable, and it is attained by a convex combination of a countably many measures from the set C (a Bayesian mixture). This was previously only known for the case when the best achievable asymptotic error is 0. This also contrasts previous results that show that in the non-realizable case all Bayesian mixtures may be suboptimal, while there is a predictor that achieves the optimal performance.
Type de document :
Communication dans un congrès
ALT 2017 - 28th International Conference on Algorithmic Learning Theory, Oct 2017, Kyoto, Japan. pp.1-13
Liste complète des métadonnées

https://hal.inria.fr/hal-01627332
Contributeur : Daniil Ryabko <>
Soumis le : mercredi 1 novembre 2017 - 09:43:28
Dernière modification le : vendredi 13 avril 2018 - 01:28:44

Lien texte intégral

Identifiants

  • HAL Id : hal-01627332, version 1
  • ARXIV : 1610.08249

Collections

Citation

Daniil Ryabko. Universality of Bayesian mixture predictors. ALT 2017 - 28th International Conference on Algorithmic Learning Theory, Oct 2017, Kyoto, Japan. pp.1-13. 〈hal-01627332〉

Partager

Métriques

Consultations de la notice

68