Title :
Density estimation consistent in information divergence
Author :
Györfi, László ; Van der Meulen, Edward C.
Author_Institution :
Dept. of Math. & Comput. Sci., Tech. Univ. Budapest, Hungary
fDate :
27 Jun-1 Jul 1994
Abstract :
We consider the problem of estimating an unknown density function f in information divergence. We prove the following theorem: for any sequence of density estimates {fn} there is a density f with finite differential entropy H(f) and with arbitrarily many derivatives such that D(f, fn)=∞ for all n
Keywords :
entropy; information theory; sequential estimation; density estimates sequence; density function estimation; finite differential entropy; information divergence; Computer science; Density functional theory; Density measurement; Entropy; Mathematics;
Conference_Titel :
Information Theory, 1994. Proceedings., 1994 IEEE International Symposium on
Conference_Location :
Trondheim
Print_ISBN :
0-7803-2015-8
DOI :
10.1109/ISIT.1994.394936
