AN INEQUALITY FOR RATIONAL FUNCTIONS WITH APPLICATIONS TO SOME STATISTICAL ESTIMATION PROBLEMS

被引：92

作者：

GOPALAKRISHNAN, PS

KANEVSKY, D

NADAS, A

NAHAMOO, D

机构：

[1] IBM Research Division, T. J. Watson Research, Yorktown Heights, NY 10598

来源：

IEEE TRANSACTIONS ON INFORMATION THEORY | 1991年 / 37卷 / 01期

关键词：

hidden; Markov models; Nonlinear optimization; speech recognition; statistical estimation;

D O I：

10.1109/18.61108

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 well-known Baum-Eagon ineauality 131 provides an effective iterative scheme for finding a local maximum for homogeneous polynomials with positive coefficients over a domain of probability values. However, in many applications we are interested in maximizing a general rational function. We extend the Baum-Eagon inequality to rational functions. We briefly describe some of the applications of this inequality to statistical estimation problems. © 1991 IEEE

引用

页码：107 / 113

页数：7

共 7 条

[1]

BAHL LR, 1983, IEEE T PATTERN ANAL, V5, P79

[2]

BAHL LR, 1986, P IEEE INT C AC SPEE, P49

[3] GROWTH TRANSFORMATIONS FOR FUNCTIONS ON MANIFOLDS [J].