The Basics of Information Geometry

Abstract

To what extent can we distinguish one probability distribution from another? Are there quantitative measures of distinguishability? The goal of this tutorial is to approach such questions by introducing the notion of the "distance" between two probability distributions and exploring some basic ideas of such an "information geometry".

13 pages. Invited tutorial presented at MaxEnt 2014, the 34th International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering (September 21--26, 2014, Amboise, France)

Cited by in corpus (8)

• Path integrals, particular kinds, and strange things
• Some interesting observations on the free energy principle
• Designing Ecosystems of Intelligence from First Principles
• Entropic dynamics on Gibbs statistical manifolds
• Length-preserving biconnection gravity and its cosmological implications
• Is the free-energy principle a formal theory of semantics? From variational density dynamics to neural and phenotypic representations
• Legendre transformation and information geometry for the maximum entropy theory of ecology
• Entropic dynamics yields reciprocal relations