Gossner, Olivier and Tomala, Tristan (2008) Entropy bounds on Bayesian learning. Journal of Mathematical Economics, 44 (1). pp. 24-32. ISSN 0304-4068
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.
|Additional Information:||© 2008 Elsevier|
|Library of Congress subject classification:||Q Science > QA Mathematics|
|Sets:||Departments > Mathematics|
|Date Deposited:||18 Feb 2009 10:58|
Actions (login required)
|Record administration - authorised staff only|