0411137 20240103182304.620060210235959.9 80-245-0546-0 Prague University of Economics 2003 6 s. 199-204VejnarováJ. Kullback-Leibler divergence information projection exponential family cav_un_auth*0101161 Matúš František UTIA-B Department of Decision Making Theory Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0213067 Ay N. DE 120 IAA1075104 GA AV ČR cav_un_auth*0001799 GA402/01/0981 GA ČR cav_un_auth*0008962 CEZ:AV0Z1075907 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*. cav_un_auth*0213068 WUPES 2003. Workshop on Uncertainty Processing /6./ Hejnice CZ 24.09.2003-27.09.2003 BA MTR http://hdl.handle.net/11104/0131224 UTIA-B 20030124 2003 2003 Prague University of Economics 80-245-0546-0 Proceedings of the 6th Workshop on Uncertainty Processing 199 204 Vejnarová J. 340