Functional Bregman Divergence and Bayesian Estimation of Distributions

DOI10.1109/TIT.2008.929943zbMATH Open1319.62137arXivcs/0611123OpenAlexW1963551385WikidataQ56690031 ScholiaQ56690031MaRDI QIDQ3604848FDOQ3604848

Authors: B. A. Frigyik, Santosh Srivastava, Maya R. Gupta 

Publication date: 24 February 2009

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Abstract: A class of distortions termed functional Bregman divergences is defined, which includes squared error and relative entropy. A functional Bregman divergence acts on functions or distributions, and generalizes the standard Bregman divergence for vectors and a previous pointwise Bregman divergence that was defined for functions. A recently published result showed that the mean minimizes the expected Bregman divergence. The new functional definition enables the extension of this result to the continuous case to show that the mean minimizes the expected functional Bregman divergence over a set of functions or distributions. It is shown how this theorem applies to the Bayesian estimation of distributions. Estimation of the uniform distribution from independent and identically drawn samples is used as a case study.

Full work available at URL: https://arxiv.org/abs/cs/0611123

Recommendations

• Re-examination of Bregman functions and new properties of their divergences
• Bregman divergence and density integration
• Parametric Bayesian estimation of differential entropy and relative entropy
• Metrics defined by Bregman divergences. II
• Metrics defined by Bregman divergences

zbMATH Keywords

uniform distributionBayesian estimationBregman divergenceconvexityFréchet derivative

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Bayesian inference (62F15) General nonlinear regression (62J02) Measures of information, entropy (94A17)

Cited In (25)

• Variational representations of annealing paths: Bregman information under monotonic embedding
• Bayesian model diagnostics using functional Bregman divergence
• Extropy: complementary dual of entropy
• An \(H\) theorem for Boltzmann's equation for the yard-sale model of asset exchange. The Gini coefficient as an \(H\) functional
• New aspects of Bregman divergence in regression and classification with parametric and nonparametric estimation
• \(\gamma\)-SUP: a clustering algorithm for cryo-electron microscopy images of asymmetric particles
• Necessary and sufficient conditions of proper estimators based on self density ratio for unnormalized statistical models
• Nonlinear Cauchy problem and identification in contact mechanics: a solving method based on Bregman-gap
• Parametric Bayesian estimation of differential entropy and relative entropy
• Nonlinear nonlocal Douglas identity
• Re-examination of Bregman functions and new properties of their divergences
• Wasserstein distances in the analysis of time series and dynamical systems
• A spectral estimation framework for phase retrieval via Bregman divergence minimization
• Bregman divergence and density integration
• Bayes Risk Error is a Bregman Divergence
• Bayesian and robust Bayesian analysis in a general setting
• Divergence-based vector quantization
• Generalized log-likelihood functions and Bregman divergences
• TYPE II TOPP-LEONE INVERSE WEIBULL DISTRIBUTION WITH STATISTICAL PROPERTIES AND APPLICATIONS
• Quasiconvex Jensen divergences and quasiconvex Bregman divergences
• Regression using localised functional Bregman divergence
• Quantization and clustering with Bregman divergences
• Title not available (Why is that?)
• Bregman divergences based on optimal design criteria and simplicial measures of dispersion
• Bayesian influence diagnostics using normalized functional Bregman divergence

This page was built for publication: Functional Bregman Divergence and Bayesian Estimation of Distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3604848)