An Application of Reversible Entropic Dynamics on Curved Statistical Manifolds
arXiv:physics/0702011 · doi:10.1063/1.2423281
Abstract
Entropic Dynamics (ED) is a theoretical framework developed to investigate the possibility that laws of physics reflect laws of inference rather than laws of nature. In this work, a RED (Reversible Entropic Dynamics) model is considered. The geometric structure underlying the curved statistical manifold, M is studied. The trajectories of this particular model are hyperbolic curves (geodesics) on M. Finally, some analysis concerning the stability of these geodesics on M is carried out.
Presented at MaxEnt 2006, the 26th International Workshop on Bayesian Inference and Maximum Entropy Methods (July 8-13, 2006, Paris, France). This paper is slightly updated from the published version. This paper consists of 9 pages with 1 figure. Keywords: Inductive inference, information geometry, statistical manifolds, relative entropy
Cited by in corpus (5)
- Information geometric methods for complexity
- Works on an information geometrodynamical approach to chaos
- Information Geometry, Inference Methods and Chaotic Energy Levels Statistics
- Information-Geometric Indicators of Chaos in Gaussian Models on Statistical Manifolds of Negative Ricci Curvature
- Theoretical investigations of an information geometric approach to complexity