A utility-based approach to some information measures (Q925767)
From MaRDI portal
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | A utility-based approach to some information measures |
scientific article |
Statements
A utility-based approach to some information measures (English)
0 references
22 May 2008
0 references
Summary: We review a decision theoretic, i.e., utility-based, motivation for entropy and Kullback-Leibler relative entropy, the natural generalizations that follow, and various properties of these generalized quantities. We then consider these generalized quantities in an easily interpreted special case. We show that the resulting quantities, share many of the properties of entropy and relative entropy, such as the data processing inequality and the second law of thermodynamics. We formulate an important statistical learning problem -- probability estimation -- in terms of a generalized relative entropy. The solution of this problem reflects general risk preferences via the utility function; moreover, the solution is optimal in a sense of robust absolute performance.
0 references
generalized entropy
0 references
generalized Kullback-Leibler relative entropy
0 references
decision theory
0 references
expected utility
0 references
horse race
0 references
Tsallis entropy
0 references
statistical learning
0 references
probability estimation
0 references
risk neutral pricing measure
0 references