A Generalization of B. S. Clarke and A. R. Barron's Asymptotics of Bayes Codes for FSMX Sources

Masayuki GOTOH; Toshiyasu MATSUSHIMA; Shigeichi HIRASAWA

A Generalization of B. S. Clarke and A. R. Barron's Asymptotics of Bayes Codes for FSMX Sources

Masayuki GOTOH, Toshiyasu MATSUSHIMA, Shigeichi HIRASAWA

Full Text Views

0

Share
Cite this

Summary :

We shall generalize B. S. Clarke and A. R. Barron 's analysis of the Bayes method for the FSMX sources. The FSMX source considered here is specified by the set of all states and its parameter value. At first, we show the asymptotic codelengths of individual sequences of the Bayes codes for the FSMX sources. Secondly, we show the asymptotic expected codelengths. The Bayesian posterior density and the maximum likelihood estimator satisfy asymptotic normality for the finite ergodic Markov source, and this is the key of our analysis.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E81-A No.10 pp.2123-2132

Publication Date: 1998/10/25

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Section on Information Theory and Its Applications)

Category: Source Coding

Cite this

Copy

Masayuki GOTOH, Toshiyasu MATSUSHIMA, Shigeichi HIRASAWA, "A Generalization of B. S. Clarke and A. R. Barron's Asymptotics of Bayes Codes for FSMX Sources" in IEICE TRANSACTIONS on Fundamentals, vol. E81-A, no. 10, pp. 2123-2132, October 1998, doi: .
Abstract: We shall generalize B. S. Clarke and A. R. Barron 's analysis of the Bayes method for the FSMX sources. The FSMX source considered here is specified by the set of all states and its parameter value. At first, we show the asymptotic codelengths of individual sequences of the Bayes codes for the FSMX sources. Secondly, we show the asymptotic expected codelengths. The Bayesian posterior density and the maximum likelihood estimator satisfy asymptotic normality for the finite ergodic Markov source, and this is the key of our analysis.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/e81-a_10_2123/_p

Copy

@ARTICLE{e81-a_10_2123,
author={Masayuki GOTOH, Toshiyasu MATSUSHIMA, Shigeichi HIRASAWA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Generalization of B. S. Clarke and A. R. Barron's Asymptotics of Bayes Codes for FSMX Sources},
year={1998},
volume={E81-A},
number={10},
pages={2123-2132},
abstract={We shall generalize B. S. Clarke and A. R. Barron 's analysis of the Bayes method for the FSMX sources. The FSMX source considered here is specified by the set of all states and its parameter value. At first, we show the asymptotic codelengths of individual sequences of the Bayes codes for the FSMX sources. Secondly, we show the asymptotic expected codelengths. The Bayesian posterior density and the maximum likelihood estimator satisfy asymptotic normality for the finite ergodic Markov source, and this is the key of our analysis.},
keywords={},
doi={},
ISSN={},
month={October},}

Copy

TY - JOUR
TI - A Generalization of B. S. Clarke and A. R. Barron's Asymptotics of Bayes Codes for FSMX Sources
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2123
EP - 2132
AU - Masayuki GOTOH
AU - Toshiyasu MATSUSHIMA
AU - Shigeichi HIRASAWA
PY - 1998
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E81-A
IS - 10
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - October 1998
AB - We shall generalize B. S. Clarke and A. R. Barron 's analysis of the Bayes method for the FSMX sources. The FSMX source considered here is specified by the set of all states and its parameter value. At first, we show the asymptotic codelengths of individual sequences of the Bayes codes for the FSMX sources. Secondly, we show the asymptotic expected codelengths. The Bayesian posterior density and the maximum likelihood estimator satisfy asymptotic normality for the finite ergodic Markov source, and this is the key of our analysis.
ER -