Počet záznamů: 1
On maximization of the information divergence from an exponential family
- 1.0411137 - UTIA-B 20030124 RIV CZ eng C - Konferenční příspěvek (zahraniční konf.)
Matúš, František - Ay, N.
On maximization of the information divergence from an exponential family.
Prague: University of Economics, 2003. ISBN 80-245-0546-0. In: Proceedings of the 6th Workshop on Uncertainty Processing. - (Vejnarová, J.), s. 199-204
[WUPES 2003. Workshop on Uncertainty Processing /6./. Hejnice (CZ), 24.09.2003-27.09.2003]
Grant CEP: GA AV ČR IAA1075104; GA ČR GA402/01/0981
Výzkumný záměr: CEZ:AV0Z1075907
Klíčová slova: Kullback-Leibler divergence * information projection * exponential family
Kód oboru RIV: BA - Obecná matematika
The information divergence of a probability measure P from an exponential family E over a finite set is defined as infimum of the divergences of P from Q subject to Q in E. For convex exponential families the local maximizers of this function of P are found. General exponential family E of dimension d is enlarged to an exponential family E* of the dimension at most 3d+2 such that the local maximizers are of zero divergence from E*.
Trvalý link: http://hdl.handle.net/11104/0131224
Počet záznamů: 1