Title :
On asymptotic equivalence of information-theoretic divergences
Author_Institution :
Inst. of Inf. Theory & Autom., Czechoslovak Acad. of Sci., Prague, Czech Republic
Abstract :
Divergences of distributions in sense of Csiszar (1963), Bregman (1967) and Burbea-Rao (1982) are considered. Asymptotic formulas for them are obtained when the probability distributions converge in a strong sense
Keywords :
information theory; probability; asymptotic equivalence; information-theoretic divergences; probability distributions; Automation; Capacity planning; Chromium; Content addressable storage; Information theory; Probability distribution; Propagation losses; Relaxation methods; Speech; Statistical analysis;
Conference_Titel :
Information Theory, 2001. Proceedings. 2001 IEEE International Symposium on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7123-2
DOI :
10.1109/ISIT.2001.935886