Duality of maximum entropy and minimum divergence

DOI10.3390/e16073552zbMath1338.62021OpenAlexW1992146538MaRDI QIDQ296478

Shinto Eguchi, Osamu Komori, Atsumi Ohara

Publication date: 15 June 2016

Published in: Entropy (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3390/e16073552

zbMATH Keywords

information geometrysufficiencymultivariate \(t\)-distribution\(\beta\)-divergencedual connectionsMaxEntpower exponential family

Mathematics Subject Classification ID

Directional data; spatial statistics (62H11) Statistical aspects of information-theoretic topics (62B10)

Related Items (3)

Dually flat geometries of the deformed exponential family ⋮ Least informative distributions in maximum \(q\)-log-likelihood estimation ⋮ Geometry of parametric binary choice models

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Group invariance of information geometry on \(q\)-Gaussian distributions induced by beta-divergence
• Nonparametric information geometry: from divergence function to referential-representational biduality on statistical manifolds
• \(F\)-geometry and Amari's \(\alpha\)-geometry on a statistical manifold
• Projective power entropy and maximum Tsallis entropy distributions
• Entropy and divergence associated with power function and the statistical application
• Families of alpha-, beta- and gamma-divergences: flexible and robust measures of similarities
• Generalised exponential families and associated entropy functions
• Robust parameter estimation with a small bias against heavy contamination
• Second order efficiency of minimum contrast estimators in a curved exponential family
• Geometry of minimum contrast
• Statistics, yokes and symplectic geometry
• Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory
• A infinite-dimensional geometric structure on the space of all the probability measures equivalent to a given one
• Possible generalization of Boltzmann-Gibbs statistics.
• Robust estimation in the normal mixture model
• Robust Blind Source Separation by Beta Divergence
• Information geometry ofq-Gaussian densities and behaviors of solutions to related diffusion equations
• Nonnegative Matrix Factorization with the Itakura-Saito Divergence: With Application to Music Analysis
• Robust and efficient estimation by minimising a density power divergence
• A class of logistic-type discriminant functions
• Robustifying AdaBoost by Adding the Naive Error Rate
• Information Geometry of U-Boost and Bregman Divergence
• Measurement of Diversity

This page was built for publication: Duality of maximum entropy and minimum divergence