Bayesian Risk with Bregman Loss: A Cramér-Rao Type Bound and Linear Estimation
Document Type
Conference Proceeding
Publication Date
3-1-2022
Abstract
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. This approach allows for the derivation of a version of the Cramér-Rao bound that is specific to a given Bregman divergence. This new generalization of the Cramér-Rao bound reduces to the classical one when the loss function is taken to be the Euclidean norm. In order to evaluate the effectiveness of the new lower bounds, the paper also develops upper bounds on Bayesian risk, which are based on optimal linear estimators. The effectiveness of the new bound is evaluated in the Poisson noise setting.
Identifier
85120070124 (Scopus)
Publication Title
IEEE Transactions on Information Theory
External Full Text Location
https://doi.org/10.1109/TIT.2021.3130381
e-ISSN
15579654
ISSN
00189448
First Page
1985
Last Page
2000
Issue
3
Volume
68
Grant
CCF-1908308
Fund Ref
National Science Foundation
Recommended Citation
Dytso, Alex; Faub, Michael; and Vincent Poor, H., "Bayesian Risk with Bregman Loss: A Cramér-Rao Type Bound and Linear Estimation" (2022). Faculty Publications. 3084.
https://digitalcommons.njit.edu/fac_pubs/3084