Limit Theorems in Hidden Markov Models

被引：9
作者：
Han, Guangyue [1 ]
机构：
[1] Univ Hong Kong, Dept Math, Hong Kong, Hong Kong, Peoples R China
来源：
IEEE TRANSACTIONS ON INFORMATION THEORY | 2013年 / 59卷 / 03期
关键词：
Entropy; hidden Markov models; limit theorem; Shannon-McMillan-Breiman theorem; MAXIMUM-LIKELIHOOD ESTIMATOR; ENTROPY;
D O I：
10.1109/TIT.2012.2226701
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper, under mild assumptions, we derive a law of large numbers, a central limit theorem with an error estimate, an almost sure invariance principle, and a variant of the Chernoff bound in finite-state hidden Markov models. These limit theorems are of interest in certain areas of information theory and statistics. Particularly, we apply the limit theorems to derive the rate of convergence of the maximum likelihood estimator in finite-state hidden Markov models.
引用
收藏
页码：1311 / 1328
页数：18
相关论文
共 48 条
[1]  
[Anonymous], 2006, Elements of Information Theory
[2]  
[Anonymous], 2007, Introduction to strong mixing conditions
[3]  
Arnold D, 2001, 2001 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS, VOLS 1-10, CONFERENCE RECORD, P2692, DOI 10.1109/ICC.2001.936639
[4]   STATISTICAL INFERENCE FOR PROBABILISTIC FUNCTIONS OF FINITE STATE MARKOV CHAINS [J].
BAUM, LE ;
PETRIE, T .
ANNALS OF MATHEMATICAL STATISTICS, 1966, 37 (06) :1554-&
[5]   The extension of the limited theorem of calculus in the probabilities of sums of independent quantities [J].
Bernstein, S .
MATHEMATISCHE ANNALEN, 1927, 97 :1-59
[6]   The accuracy of the Gaussian approximation to the sum of independent variates [J].
Berry, Andrew C. .
TRANSACTIONS OF THE AMERICAN MATHEMATICAL SOCIETY, 1941, 49 (1-3) :122-136
[7]  
Bickel P. J., 1996, Bernoulli, V2, P199
[8]  
Bickel PJ, 1998, ANN STAT, V26, P1614
[9]  
Billingsley Patrick, 1995, Probability and Measure
[10]   APPROXIMATIONS FOR ENTROPY FOR FUNCTIONS OF MARKOV-CHAINS [J].
BIRCH, JJ .
ANNALS OF MATHEMATICAL STATISTICS, 1962, 33 (03) :930-+
12345