Functional Bregman Divergence and Bayesian Estimation of Distributions (Preprint)
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. We have defined a general Bregman divergence for functions and distributions that can provide a foundation for results in statistics, information theory and signal processing.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2008
- Accession Number
- ADA479637
Entities
People
- B. A. Frigyik
- M. R. Gupta
- Shivani Srivastava
Organizations
- Purdue University