Title :
Universal Consistency of Data-Driven Partitions for Divergence Estimation
Author :
Silva, J. ; Narayanan, S.
Author_Institution :
Viterbi Sch. of Eng., Univ. of Southern California, Los Angeles, CA
Abstract :
This paper presents a general histogram based divergence estimator based on data-dependent partition. Sufficient conditions for the universal strong consistency of the data-driven divergence estimator, using Lugosi and Nobel´s combinatorial notions for partition families, are presented. As a corollary this result is particularized for the emblematic case of l m-spacing quantization scheme.
Keywords :
combinatorial mathematics; estimation theory; information theory; combinatorial notions; data-dependent partition; data-driven partitions; divergence estimation; partition families; spacing quantization; universal consistency; Data engineering; Entropy; Histograms; Laboratories; Length measurement; Q measurement; Quantization; Signal analysis; Sufficient conditions; Viterbi algorithm;
Conference_Titel :
Information Theory, 2007. ISIT 2007. IEEE International Symposium on
Conference_Location :
Nice
Print_ISBN :
978-1-4244-1397-3
DOI :
10.1109/ISIT.2007.4557518
