Title :
Generalized projections for non-negative functions
Author_Institution :
Math. Inst., Hungarian Acad. of Sci., Budapest, Hungary
Abstract :
The problem of minimizing a functional over a convex set of non-negative functions is considered, when the functional to be minimized is an f-entropy, or f-divergence resp. Bregman distance from a given function
Keywords :
functional analysis; functions; information theory; maximum entropy methods; minimisation; Bregman distance; convex set; f-divergence; f-entropy; functional minimization; generalized projections; maximum entropy type methods; nonnegative functions; Convergence; Entropy; Q measurement; Random variables; Sufficient conditions;
Conference_Titel :
Information Theory, 1995. Proceedings., 1995 IEEE International Symposium on
Conference_Location :
Whistler, BC
Print_ISBN :
0-7803-2453-6
DOI :
10.1109/ISIT.1995.531108
