Maximizing the Bregman divergence from a Bregman family

DOI10.14736/kyb-2020-5-0875OpenAlexW3112976351MaRDI QIDQ5858539

Johannes Rauh, František Matúš

Publication date: 13 April 2021

Published in: Kybernetika (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2001.08813

zbMATH Keywords

optimizationrelative entropyexponential familyBregman divergence

Mathematics Subject Classification ID

Exact distribution theory in statistics (62E15) Convex functions and convex programs in convex geometry (52A41) Approximations to statistical distributions (nonasymptotic) (62E17) Measures of information, entropy (94A17) Sufficient statistics and fields (62B05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Closures of exponential families
• An information-geometric approach to a theory of pragmatic structuring
• Approximating faces of marginal polytopes in discrete hierarchical models
• Generalized maximum likelihood estimates for exponential families
• On the toric algebra of graphical models
• Information and Exponential Families
• Generalized minimizers of convex integral functionals, Bregman distance, Pythagorean identities
• Divergence From Factorizable Distributions and Matroid Representations by Partitions
• Finding the Maximizers of the Information Divergence From an Exponential Family
• Maximal Information Divergence from Statistical Models Defined by Neural Networks

This page was built for publication: Maximizing the Bregman divergence from a Bregman family