DocumentCode
3643616
Title
Maximization of the information divergence from an exponential family and criticality
Author
František Matúš;Johannes Rauh
Author_Institution
Institute of Information Theory and Automation, Academy of Sciences of the Czech Republic, Pod vodá
fYear
2011
fDate
7/1/2011 12:00:00 AM
Firstpage
903
Lastpage
907
Abstract
The problem to maximize the information divergence from an exponential family is compared to the maximization of an entropy-like quantity over the boundary of a polytope. First-order conditions on directional derivatives define critical sets for the two problems. The bijection between the sets of global maximizers in the two problems found earlier is extended here to bijections between the sets of local maximizers and the critical sets. This is based on new inequalities relating the maximized quantities and a reformulation of the first order criticality conditions for the second problem.
Keywords
"Atmospheric measurements","Particle measurements","Information theory","Vectors","Neural networks","Calculus"
Publisher
ieee
Conference_Titel
Information Theory Proceedings (ISIT), 2011 IEEE International Symposium on
ISSN
2157-8095
Print_ISBN
978-1-4577-0596-0
Electronic_ISBN
2157-8117
Type
conf
DOI
10.1109/ISIT.2011.6034269
Filename
6034269
Link To Document