Approximation of Bayes code for Markov sources

Jun ichi Takeuchi, Tsutomu Kawabata

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

An approximation formula for the predictive Bayes code for the FSMX models, subspaces of Markov models, is presented. It is empirically shown that the code using the approximation formula along with the Jeffreys prior (Clark et al, 1994) gives shorter code length than the one using the Laplace estimator for the first order Markov models. It is also shown that there is difficulty in introducing the formula to CONTEXT or CTW methods.

Original languageEnglish
Number of pages1
Publication statusPublished - Jan 1 1995
Externally publishedYes
EventProceedings of the 1995 IEEE International Symposium on Information Theory - Whistler, BC, Can
Duration: Sep 17 1995Sep 22 1995

Other

OtherProceedings of the 1995 IEEE International Symposium on Information Theory
CityWhistler, BC, Can
Period9/17/959/22/95

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Information Systems
  • Modelling and Simulation
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Approximation of Bayes code for Markov sources'. Together they form a unique fingerprint.

  • Cite this

    Takeuchi, J. I., & Kawabata, T. (1995). Approximation of Bayes code for Markov sources. Paper presented at Proceedings of the 1995 IEEE International Symposium on Information Theory, Whistler, BC, Can, .