Information geometry on complexity and stochastic interaction

Nihat Ay
(Please use for correspondence this email).

Submission date: 07. Dec. 2001
Pages: 35
Keywords and phrases: stochastic interaction, complexity, information geometry, kullback-leibler divergence, separability, markov chains, random fields
Download preprint: PDF (486 kB), PS ziped (229 kB)

Abstract:
Interdependencies of stochastically interacting units are usually quantified by the Kullback-Leibler divergence of a stationary joint probability distribution on the set of all configurations from the corresponding factorized distribution. This is a spatial approach which does not describe the intrinsically temporal aspects of interaction. In the present paper the setting is extended to a dynamical version where temporal interdependencies are also captured by using information geometry of Markov-chain manifolds.