Chentsov's theorem for exponential families

DOI10.1007/s41884-018-0006-4zbMath1409.62021arXiv1701.08895OpenAlexW2963996902WikidataQ115600301 ScholiaQ115600301MaRDI QIDQ1713653

James G. Dowty

Publication date: 28 January 2019

Published in: Information Geometry (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1701.08895

zbMATH Keywords

Riemannian metricinformation geometryFisher information metriccurved exponential familiesChentsov's theorem

Mathematics Subject Classification ID

Probability distributions: general theory (60E05) Applications of global differential geometry to the sciences (53C80) Statistical aspects of information-theoretic topics (62B10)

Related Items (5)

Chentsov's theorem for exponential families ⋮ A characterization of the alpha-connections on the statistical manifold of normal distributions ⋮ Information geometry ⋮ Clustering in Hilbert’s Projective Geometry: The Case Studies of the Probability Simplex and the Elliptope of Correlation Matrices ⋮ From Hessian to Weitzenböck: manifolds with torsion-carrying connections

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Chentsov's theorem for exponential families
• A infinite-dimensional geometric structure on the space of all the probability measures equivalent to a given one
• Information geometry and sufficient statistics
• Congruent families and invariant tensors
• Uniqueness of the Fisher–Rao metric on the space of smooth densities
• An Extended Cencov Characterization of the Information Metric
• Algebraic foundation of mathematical statistics²
• The minimum description length principle in coding and modeling
• Fisher information and stochastic complexity
• Sufficient Data Reduction and Exponential Families.

This page was built for publication: Chentsov's theorem for exponential families