Divergence estimation of continuous distributions based on data-dependent partitions

We present a universal estimator of the divergence D(P/spl par/Q) for two arbitrary continuous distributions P and Q satisfying certain regularity conditions. This algorithm, which observes independent and identically distributed (i.i.d.) samples from both P and Q, is based on the estimation of the...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on information theory 2005-09, Vol.51 (9), p.3064-3074
Hauptverfasser:	Qing Wang, Kulkarni, S.R., Verdu, S.
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Applied sciences Bias correction Computer simulation Convergence data-dependent partition Density measurement Derivatives Detection, estimation, filtering, equalization, prediction Divergence Entropy Equivalence Estimators Exact sciences and technology Extraterrestrial measurements Information systems Information theory Information, signal and communications theory Mutual information Partitioning Partitioning algorithms Partitions Pattern recognition Radon-Nikodym derivative Random variables Signal and communications theory Signal, noise stationary and ergodic data Telecommunications and information theory Testing universal estimation of information measures
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!