Skip to Main content Skip to Navigation
Conference papers

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 - 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.
Complete list of metadata
Contributor : Daniil Ryabko Connect in order to contact the contributor
Submitted on : Wednesday, November 1, 2017 - 9:43:28 AM
Last modification on : Friday, January 7, 2022 - 3:44:00 AM

Links full text


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


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⟩



Les métriques sont temporairement indisponibles