Entropy bounds on Bayesian learning

Abstract : An observer of a process View the MathML source believes the process is governed by Q whereas the true law is P. We bound the expected average distance between P(xt|x1,...,xt−1) and Q(xt|x1,...,xt−1) for t=1,...,n by a function of the relative entropy between the marginals of P and Q on the n first realizations. We apply this bound to the cost of learning in sequential decision problems and to the merging of Q to P.
Type de document :
Article dans une revue
Journal of Mathematical Economics, Elsevier, 2008, 44 (1), pp.24-32. 〈10.1016/j.jmateco.2007.04.006〉
Liste complète des métadonnées

https://hal-pjse.archives-ouvertes.fr/halshs-00754314
Contributeur : Caroline Bauer <>
Soumis le : mardi 20 novembre 2012 - 08:54:28
Dernière modification le : mardi 24 avril 2018 - 17:20:09

Lien texte intégral

Identifiants

Collections

Citation

Olivier Gossner, Tristan Tomala. Entropy bounds on Bayesian learning. Journal of Mathematical Economics, Elsevier, 2008, 44 (1), pp.24-32. 〈10.1016/j.jmateco.2007.04.006〉. 〈halshs-00754314〉

Partager

Métriques

Consultations de la notice

290