Estimation of the information by an adaptive partitioning of the observation space

被引：350

作者：

Darbellay, GA ^{[1
]}

Vajda, I ^{[1
]}

机构：

[1] Acad Sci Czech Republ, Inst Informat Theory & Automat, CR-18208 Prague, Czech Republic

来源：

IEEE TRANSACTIONS ON INFORMATION THEORY | 1999年 / 45卷 / 04期

关键词：

data-dependent partitions; maximum-likelihood estimation; mutual information; nonparametric estimation;

D O I：

10.1109/18.761290

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We demonstrate that it is possible to approximate the mutual information arbitrarily closely in probability by calculating relative frequencies on appropriate partitions and achieving conditional independence on the rectangles of which the partitions are made. Empirical results, including a comparison with maximum-likelihood estimators, are presented.

引用

页码：1315 / 1321

页数：7

共 17 条

[1]

[Anonymous], 1992, MULTIVARIATE DENSITY

[2] DISTRIBUTION ESTIMATION CONSISTENT IN TOTAL VARIATION AND IN 2 TYPES OF INFORMATION DIVERGENCE [J].

BARRON, AR ;

GYORFI, L ;

VANDERMEULEN, EC .

IEEE TRANSACTIONS ON INFORMATION THEORY, 1992, 38 (05) :1437-1454

[3]

Beirlant J, 1997, INT J MATH STAT SCI, V6, P17

[4]

BOFINGER E, 1973, J ROY STAT SOC B, V35, P277

[5]

CIZOVA I, 1997, THESIS CVUT CZECH TU

[6]

Cover T. M., 2005, ELEM INF THEORY, DOI 10.1002/047174882X

[7]

Darbellay G. A., 1997, Proceeding. 1997 IEEE International Symposium on Information Theory (Cat. No.97CH36074), DOI 10.1109/ISIT.1997.613342

[8]

Darbellay GA, 1998, APPL NUM HARM ANAL, P249

[9]

DARBELLAY GA, 1998, P 3 EUR IEEE WORKSH

[10]

DARBELLAY GA, IN PRESS COMPUTAT ST

← 1 2 →