Reexamination of an Information Geometric Construction of Entropic Indicators of Complexity

TL;DR

This paper reexamines the information geometric approach to defining entropic indicators of complexity, focusing on the interpretation of the information geometric entropy (IGE) as a measure of chaos in probabilistic dynamical systems.

Contribution

It provides a conceptual reanalysis and advances the understanding of IGE within the framework of information geometry for physical systems.

Findings

Clarified the interpretation of IGE as a complexity measure

Enhanced the conceptual framework of information geometric indicators

Improved understanding of entropy in probabilistic dynamical systems

Abstract

Information geometry and inductive inference methods can be used to model dynamical systems in terms of their probabilistic description on curved statistical manifolds. In this article, we present a formal conceptual reexamination of the information geometric construction of entropic indicators of complexity for statistical models. Specifically, we present conceptual advances in the interpretation of the information geometric entropy (IGE), a statistical indicator of temporal complexity (chaoticity) defined on curved statistical manifolds underlying the probabilistic dynamics of physical systems.