Closures of exponential families

DOI10.1214/009117904000000766zbMath1068.60008arXivmath/0503653OpenAlexW2086776773MaRDI QIDQ1775441

Imre Csiszár, František Matúš

Publication date: 3 May 2005

Published in: The Annals of Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/math/0503653

zbMATH Keywords

weak convergenceextensionclosure propertiesinformation divergenceconvex supportconvex corevariation distanceexponential family of probability measuresaccessible facereverse information divergence

Mathematics Subject Classification ID

Probabilistic measure theory (60A10) Convergence of probability measures (60B10) Statistical aspects of information-theoretic topics (62B10) Convex sets in (n) dimensions (including convex hypersurfaces) (52A20)

Related Items (11)

Computing with Fisher geodesics and extended exponential families ⋮ On limiting towards the boundaries of exponential families ⋮ Geometry and applied statistics ⋮ On the geometry of discrete exponential families with application to exponential random graph models ⋮ Maximum likelihood estimation in log-linear models ⋮ Generalized maximum likelihood estimates for exponential families ⋮ Support sets in exponential families and oriented matroid theory ⋮ Quantum convex support ⋮ Computationally efficient likelihood inference in exponential families when the maximum likelihood estimator does not exist ⋮ Unnamed Item ⋮ Maximizing the Bregman divergence from a Bregman family

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Sanov property, generalized I-projection and a conditional limit theorem
• On Information Closures of Exponential Families: A Counterexample
• Information projections revisited
• Convex cores of measures on R d
• Convex Analysis

This page was built for publication: Closures of exponential families