Things Bayes can't do - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Things Bayes can't do

Daniil Ryabko
  • Fonction : Auteur
  • PersonId : 848126

Résumé

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.

Dates et versions

hal-01380063 , version 1 (12-10-2016)

Identifiants

Citer

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

Altmetric

Partager

Gmail Facebook X LinkedIn More