Skip to main content
top

Bibliography

Conference Paper (international conference)

On maximization of the information divergence from an exponential family

Matúš František, Ay N.

: Proceedings of the 6th Workshop on Uncertainty Processing, p. 199-204 , Eds: Vejnarová J.

: University of Economics, (Prague 2003)

: WUPES 2003. Workshop on Uncertainty Processing /6./, (Hejnice, CZ, 24.09.2003-27.09.2003)

: CEZ:AV0Z1075907

: IAA1075104, GA AV ČR, GA402/01/0981, GA ČR

: Kullback-Leibler divergence, information projection, exponential family

(eng): 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*.

: 120

: BA