Cahiers du CEREMADE

Unité Mixte de Recherche du C.N.R.S. N°7534
Abstract : An observer of a process (Xt) believes the process is governed by Q whereas the true law is P. We bound the expected average L1 distance between the stage-conditional distributions of P and Q 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.
Entropy Bounds on Bayesian Learning
GOSSNER Olivier, TOMALA Tristan
Université de PARIS - DAUPHINE
Place du Maréchal de Lattre De Tassigny - 75775 PARIS CEDEX 16 - FRANCE
Téléphone : +33 (0)1 44-05-49-23 - fax : +33 (0)1 44-05-45-99