The exponential family of Markov chains and its information geometry
Information Theory
2017-01-24 v1 math.IT
Abstract
We introduce a new definition of exponential family of Markov chains, and show that many characteristic properties of the usual exponential family of probability distributions are properly extended to Markov chains. The method of information geometry is effectively applied to our framework, which enables us to characterize the divergence rate of Markov chain from a differential geometric viewpoint.
Keywords
Cite
@article{arxiv.1701.06119,
title = {The exponential family of Markov chains and its information geometry},
author = {Hiroshi Nagaoka},
journal= {arXiv preprint arXiv:1701.06119},
year = {2017}
}
Comments
This work was presented in the 28th Symposium on Information Theory and Its Applications (SITA2005) in 2005