Title :
On the practical implication of mutual information for statistical decisionmaking
Author :
Kanaya, F. ; Nakagawa, Koichi
Author_Institution :
NTT Transmission Syst. Lab., Kanagawa
fDate :
7/1/1991 12:00:00 AM
Abstract :
A basic mathematical function that conjoins the two key conceptions of mutual information and Bayes risk is defined. Based on that function, some asymptotic theorems that verify an important implication of mutual information in the context of practical Bayesian decisionmaking are proven
Keywords :
Bayes methods; decision theory; information theory; Bayes risk; asymptotic theorems; basic mathematical function; mutual information; practical implication; statistical decisionmaking; Bayesian methods; Convergence; Decision theory; Frequency; Information theory; Mutual information; Pattern recognition; Random variables; Rate distortion theory; Rate-distortion;
Journal_Title :
Information Theory, IEEE Transactions on