Information Geometry: Geometrization of Science of Information
Abstract
Information geometry is an emerging mathematical framework for modeling the space ofprobability density functions as forming a (possibly infinite-dimensional) differentiablemanifold equipped with a Riemannian metric and a pair of conjugate connections thatneed not be metrical. Information geometry has so far been applied to many disciplinessuch as asymptotic statistics, Bayesian inference, information theory and coding, machinelearning, neural computation, econometrics, cognitive psychology, etc. It is seen by someas a potentially unifying framework for geometrizing information in the same way thatphysics has been geometrized.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 14, 2017
- Accession Number
- AD1097196
Entities
People
- Jun Zhang
Organizations
- University of Michigan