TY - GEN

T1 - Information geometry of the family of Markov kernels defined by a context tree

AU - Takeuchi, Jun'Ichi

AU - Nagaoka, Hiroshi

PY - 2018/1/31

Y1 - 2018/1/31

N2 - We prove that a tree model is an exponential family (e-family) of Markov kernels, if and only if it is an FSMX model. The notion of e-family of Markov kernels was first introduced by Nakagawa and Kanaya ('93) in the one-dimensional case. Then, Nagaoka ('05) gave its established form, and Hayashi & Watanabe ('16) discussed it. A tree model is the Markov model defined by a context tree. It is noted by Weinberger et al., ('95) that tree models are classified into two classes; FSMX models and non-FSMX models, depending on the shape of their context trees. The FSMX model is a tree model and a finite state machine. We further show that, for Markov models, the e-family of Markov kernels is equivalent to the asymptotic e-family, which was introduced by Takeuchi & Barron ('98). Note that Takeuchi & Kawabata ('07) proved that non-FSMX tree models are not asymptotic e-families for the binary alphabet case. This paper enhances their result and reveals the information geometrical properties of tree models.

AB - We prove that a tree model is an exponential family (e-family) of Markov kernels, if and only if it is an FSMX model. The notion of e-family of Markov kernels was first introduced by Nakagawa and Kanaya ('93) in the one-dimensional case. Then, Nagaoka ('05) gave its established form, and Hayashi & Watanabe ('16) discussed it. A tree model is the Markov model defined by a context tree. It is noted by Weinberger et al., ('95) that tree models are classified into two classes; FSMX models and non-FSMX models, depending on the shape of their context trees. The FSMX model is a tree model and a finite state machine. We further show that, for Markov models, the e-family of Markov kernels is equivalent to the asymptotic e-family, which was introduced by Takeuchi & Barron ('98). Note that Takeuchi & Kawabata ('07) proved that non-FSMX tree models are not asymptotic e-families for the binary alphabet case. This paper enhances their result and reveals the information geometrical properties of tree models.

UR - http://www.scopus.com/inward/record.url?scp=85046370905&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046370905&partnerID=8YFLogxK

U2 - 10.1109/ITW.2017.8278008

DO - 10.1109/ITW.2017.8278008

M3 - Conference contribution

AN - SCOPUS:85046370905

T3 - IEEE International Symposium on Information Theory - Proceedings

SP - 429

EP - 433

BT - 2017 IEEE Information Theory Workshop, ITW 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 IEEE Information Theory Workshop, ITW 2017

Y2 - 6 November 2017 through 10 November 2017

ER -