Cookies?
Library Header Image
LSE Research Online LSE Library Services

Entropy bounds on Bayesian learning

Gossner, Olivier and Tomala, Tristan (2008) Entropy bounds on Bayesian learning. Journal of Mathematical Economics, 44 (1). pp. 24-32. ISSN 0304-4068

Full text not available from this repository.
Identification Number: 10.1016/j.jmateco.2007.04.006

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.

Item Type: Article
Official URL: http://www.sciencedirect.com/science/journal/03044...
Additional Information: © 2008 Elsevier
Subjects: Q Science > QA Mathematics
Sets: Departments > Mathematics
Date Deposited: 18 Feb 2009 10:58
Last Modified: 01 Oct 2010 09:21
URI: http://eprints.lse.ac.uk/id/eprint/22723

Actions (login required)

View Item View Item