Abstract

We give an interpretation of the Maximum Entropy (MaxEnt) Principle in gametheoretic terms. Based on this interpretation, we makeaformal distinction between different ways of applying Maximum Entropy distributions. MaxEnt has frequently been criticized on the grounds that it leads to highly representation dependent results. Our distinction allows us to avoid this problem in many cases.

Citations

6514	Elements of Information Theory - Cover, Thomas - 1991
917	Statistical decision theory and Bayesian analysis - Berger - 1985
451	Bayesian Network Classifiers - Friedman, Geiger, et al. - 1997
65	The Minimum Description Length Principle and Reasoning - Grünwald - 1998
44	Random worlds and maximum entropy - Grove, Halpern, et al. - 1994
38	Papers on probability, statistics and statistical physics, Ed. by R.D. Rosenkrantz, D.Reidel Publishing Company - Jaynes - 1983
26	A general minimax result for relative entropy - Haussler - 1997
18	Representation dependence in probabilistic inference - Halpern, Koller - 1995
15	Bayesian network classi ers - Friedmann, Geiger, et al. - 1997
1	Robust Bayes and maximum generalised entropy - Dawid - 2000