Exponential curvature of Markov models

Junnichi Takeuchi, Tsutomu Kawabata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

We prove that the non FSMX tree model is not an exponential family. It is noted in [Weinberger et al., 95] that the tree source is classified into two classes; a FSMX source or not, depending on shape of the context tree. The FSMX source is a tree source and a finite state machine. It is known that the FSMX model is an exponential family. In this situation our concern is whether the non FSMX tree model is an exponential family or not. This paper's contribution is to show that the non FSMX tree model is not an exponential family. Hence, for the tree model, to be an FSMX model is a necessary and sufficient condition for to be an exponential family.

Original languageEnglish
Title of host publicationProceedings - 2007 IEEE International Symposium on Information Theory, ISIT 2007
Pages2891-2895
Number of pages5
DOIs
Publication statusPublished - Dec 1 2007
Event2007 IEEE International Symposium on Information Theory, ISIT 2007 - Nice, France
Duration: Jun 24 2007Jun 29 2007

Publication series

NameIEEE International Symposium on Information Theory - Proceedings
ISSN (Print)2157-8101

Other

Other2007 IEEE International Symposium on Information Theory, ISIT 2007
CountryFrance
CityNice
Period6/24/076/29/07

    Fingerprint

All Science Journal Classification (ASJC) codes

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

Cite this

Takeuchi, J., & Kawabata, T. (2007). Exponential curvature of Markov models. In Proceedings - 2007 IEEE International Symposium on Information Theory, ISIT 2007 (pp. 2891-2895). [4557657] (IEEE International Symposium on Information Theory - Proceedings). https://doi.org/10.1109/ISIT.2007.4557657