Entropy Bounds on Bayesian Learning

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.

MoreLess

Year of publication:	2008
Authors:	Gossner, Olivier ; Tomala, Tristan
Institutions:	Université Paris-Dauphine (Paris IX)
Subject:	Bayesian learning \| Repeated decision problem \| Value of information \| Entropy

More details

Extent:	application/pdf
Series:	Economics Papers from University Paris Dauphine.
Type of publication:	Book / Working Paper
Notes:	Published in Journal of Mathematical Economics, 2008, Vol. 44, no. 1. pp. 24-32.Length: 8 pages
Classification:	C11 - Bayesian Analysis
Source:	RePEc - Research Papers in Economics

Persistent link: https://ebvufind01.dmz1.zbw.eu/10011073630