ON THE PRACTICAL IMPLICATION OF MUTUAL INFORMATION FOR STATISTICAL DECISION-MAKING

被引：15

作者：

KANAYA, F

NAKAGAWA, K

机构：

[1] NTT Transmission Systems Laboratories, Kanagawa, 238-03

来源：

IEEE TRANSACTIONS ON INFORMATION THEORY | 1991年 / 37卷 / 04期

关键词：

RATE-DISTORTION THEORY; STATISTICAL DECISION THEORY; BAYES RISK; MUTUAL INFORMATION; RATE-DISTORTION FUNCTION;

D O I：

10.1109/18.87006

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A basic mathematical function that conjoins the two key conceptions of mutual information and Bayes risk is defined. Then based on that function, some asymptotic theorems that verify an important implication of mutual information in the context of practical Bayesian decisionmaking are proven.

引用

页码：1151 / 1155

页数：5

共 6 条

[1]

Berger T., 2003, WILEY ENCY TELECOMMU

[2]

CSISZAR I, 1981, INFORMATION THEORY C

[3]

GALLAGER RG, 1968, INFORMATION THEORY R

[4]

Guiasu S, 1977, INFORMATION THEORY A

[5] TOWARD A FUNDAMENTAL THEORY OF OPTIMAL FEATURE-SELECTION .1. [J].

MORGERA, SD ;

DATTA, L .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1984, 6 (05) :601-616

[6] DOMINANCE - A RELATION BETWEEN DISTORTION MEASURES [J].

STJERNVALL, JE .

IEEE TRANSACTIONS ON INFORMATION THEORY, 1983, 29 (06) :798-807

← 1 →