MINIMUM COMPLEXITY DENSITY-ESTIMATION

被引：268

作者：

BARRON, AR

COVER, TM

机构：

[1] UNIV ILLINOIS,DEPT ELECT & COMP ENGN,CHAMPAIGN,IL 61820

[2] STANFORD UNIV,INFORMAT SYST LAB,STANFORD,CA 94305

来源：

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

基金：

美国国家科学基金会;

关键词：

KOLMOGOROV COMPLEXITY; MINIMUM DESCRIPTION-LENGTH CRITERION; UNIVERSAL DATA COMPRESSION; BOUNDS ON REDUNDANCY; RESOLVABILITY OF FUNCTIONS; MODEL SELECTION; DENSITY ESTIMATION; DISCOVERY OF PROBABILITY LAWS; CONSISTENCY; STATISTICAL CONVERGENCE RATES;

D O I：

10.1109/18.86996

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The minimum complexity or minimum description-length criterion developed by Kolmogorov, Rissanen, Wallace, Sorkin, and others leads to consistent probability density estimators. These density estimators are defined to achieve the best compromise between likelihood and simplicity. A related issue is the compromise between accuracy of approximations and complexity relative to the sample size. An index of resolvability is studied which is shown to bound the statistical accuracy of the density estimators, as well as the information-theoretic redundancy.

引用

页码：1034 / 1054

页数：21