Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory

Details Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory

2004-10-05

arxiv.org/abs/math/0410076v1

Annals of Statistics 2004, Vol. 32, No. 4, 1367-1433

Mathematics

Statistics Theory

Published by the Institute of Mathematical Statistics (http://www.imstat.org) in the Annals of Statistics (http://www.imstat

Scientific paper

10.1214/009053604000000553

We describe and develop a close relationship between two problems that have customarily been regarded as distinct: that of maximizing entropy, and that of minimizing worst-case expected loss. Using a formulation grounded in the equilibrium theory of zero-sum games between Decision Maker and Nature, these two problems are shown to be dual to each other, the solution to each providing that to the other. Although Tops\oe described this connection for the Shannon entropy over 20 years ago, it does not appear to be widely known even in that important special case. We here generalize this theory to apply to arbitrary decision problems and loss functions. We indicate how an appropriate generalized definition of entropy can be associated with such a problem, and we show that, subject to certain regularity conditions, the above-mentioned duality continues to apply in this extended context. This simultaneously provides a possible rationale for maximizing entropy and a tool for finding robust Bayes acts. We also describe the essential identity between the problem of maximizing entropy and that of minimizing a related discrepancy or divergence between distributions. This leads to an extension, to arbitrary discrepancies, of a well-known minimax theorem for the case of Kullback-Leibler divergence (the ``redundancy-capacity theorem'' of information theory). For the important case of families of distributions having certain mean values specified, we develop simple sufficient conditions and methods for identifying the desired solutions.

Affiliated with

Also associated with

No associations

Rating

Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-103148