Maximization of the information divergence from an exponential family and criticality

0363274 - ÚTIA 2012 RIV RU eng C - Konferenční příspěvek (zahraniční konf.)
Matúš, František - Rauh, J.
Maximization of the information divergence from an exponential family and criticality.
Proceedings ISIT 2011. Piscataway: IEEE, 2011, s. 903-907. ISBN 978-1-4577-0595-3.
[IEEE Internation Symposioum on Information Theory. St. Petersburg (RU), 31.07.2011-05.08.2011]
Grant CEP: GA ČR GAP202/10/0618
Výzkumný záměr: CEZ:AV0Z10750506
Klíčová slova: exponential family * information divergence * critical sets
Kód oboru RIV: BD - Teorie informace
http://library.utia.cas.cz/separaty/2011/MTR/matus-maximization of the information divergence from an exponential family and criticality.pdf

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.
Trvalý link: http://hdl.handle.net/11104/0199266