A Class of Lower Bounds for Bayesian Risk with a Bregman Loss

Saved in:
Bibliographic Details
Main Author Alex Dytso
Format Streaming Video
LanguageEnglish
Published IEEE 2020
Online AccessGet more information

Cover

More Information
Bibliography:A general class of Bayesian lower bounds when the underlying loss function is a Bregman divergence is demonstrated. This class can be considered as an extension of the Weinstein-Weiss family of bounds for the mean squared error and relies on finding a variational characterization of Bayesian risk. The approach allows for the derivation of a version of the Cramér-Rao bound that is specific to a given Bregman divergence. The effectiveness of the new bound is evaluated in the Poisson noise setting.
Presenter: Alex Dytso, SPAWC 2020, Virtual Event, May 26-29, 2020
DOI:10.17023/bxan-2r08