Things Bayes can't do

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 of forecasting conditional probabilities of the next event given the past is considered in a general probabilistic setting. Given an arbitrary (large, uncountable) set C of predictors, we would like to construct a single predictor that performs asymptotically as well as the best predictor in C, on any data. Here we show that there are sets C for which such predictors exist, but none of them is a Bayesian predictor with a prior concentrated on C. In other words, there is a predictor with sublinear regret, but every Bayesian predictor must have a linear regret. This negative finding is in sharp contrast with previous results that establish the opposite for the case when one of the predictors in C achieves asymptotically vanishing error. In such a case, if there is a predictor that achieves asymptotically vanishing error for any measure in C, then there is a Bayesian predictor that also has this property, and whose prior is concentrated on (a countable subset of) C.
Type de document :
Communication dans un congrès
Proceedings of the 27th International Conference on Algorithmic Learning Theory (ALT'16), Oct 2016, Bari, Italy. LNCS ( 9925), pp.253-260, 2016, 〈10.1007/978-3-319-46379-7_17〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01380063
Contributeur : Daniil Ryabko <>
Soumis le : mercredi 12 octobre 2016 - 14:13:35
Dernière modification le : mardi 3 juillet 2018 - 11:40:28

Lien texte intégral

Identifiants

Collections

Citation

Daniil Ryabko. Things Bayes can't do. Proceedings of the 27th International Conference on Algorithmic Learning Theory (ALT'16), Oct 2016, Bari, Italy. LNCS ( 9925), pp.253-260, 2016, 〈10.1007/978-3-319-46379-7_17〉. 〈hal-01380063〉

Partager

Métriques

Consultations de la notice

140