A fresh look at the Bayesian bounds of the Weiss-Weinstein family

Alexandre Renaux, Philippe Forster, Pascal Larzabal, Christ Richmond, Arye Nehorai

Research output: Contribution to journalArticle

43 Citations (Scopus)

Abstract

Minimal bounds on the mean square error (MSE) are generally used in order to predict the best achievable performance of an estimator for a given observation model. In this paper, we are interested in the Bayesian bound of the Weiss-Weinstein family. Among this family, we have Bayesian Cramér-Rao bound, the Bobrovsky-MayerWolf-Zakaï bound, the Bayesian Bhattacharyya bound, the Bobrovsky-Zakaï bound, the Reuven-Messer bound, and the Weiss-Weinstein bound. We present a unification of all these minimal bounds based on a rewriting of the minimum mean square error estimator (MMSEE) and on a constrained optimization problem. With this approach, we obtain a useful theoretical framework to derive new Bayesian bounds. For that purpose, we propose two bounds. First, we propose a generalization of the Bayesian Bhattacharyya bound extending the works of Bobrovsky, Mayer-Wolf, and Zakaï. Second, we propose a bound based on the Bayesian Bhattacharyya bound and on the Reuven-Messer bound, representing a generalization of these bounds. The proposed bound is the Bayesian extension of the deterministic Abel bound and is found to be tighter than the Bayesian Bhattacharyya bound, the Reuven-Messer bound, the Bobrovsky-Zakaï bound, and the Bayesian Cramér-Rao bound. We propose some closed-form expressions of these bounds for a general Gaussian observation model with parameterized mean. In order to illustrate our results, we present simulation results in the context of a spectral analysis problem.

Original languageEnglish (US)
Pages (from-to)5334-5352
Number of pages19
JournalIEEE Transactions on Signal Processing
Volume56
Issue number11
DOIs
StatePublished - Nov 3 2008
Externally publishedYes

Fingerprint

Mean square error
Constrained optimization
Spectrum analysis

Keywords

  • Bayesian bounds on the MSE
  • Weiss-Weinstein family

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

A fresh look at the Bayesian bounds of the Weiss-Weinstein family. / Renaux, Alexandre; Forster, Philippe; Larzabal, Pascal; Richmond, Christ; Nehorai, Arye.

In: IEEE Transactions on Signal Processing, Vol. 56, No. 11, 03.11.2008, p. 5334-5352.

Research output: Contribution to journalArticle

Renaux, Alexandre ; Forster, Philippe ; Larzabal, Pascal ; Richmond, Christ ; Nehorai, Arye. / A fresh look at the Bayesian bounds of the Weiss-Weinstein family. In: IEEE Transactions on Signal Processing. 2008 ; Vol. 56, No. 11. pp. 5334-5352.
@article{67e18f304f6f4d92bc0642eb25447850,
title = "A fresh look at the Bayesian bounds of the Weiss-Weinstein family",
abstract = "Minimal bounds on the mean square error (MSE) are generally used in order to predict the best achievable performance of an estimator for a given observation model. In this paper, we are interested in the Bayesian bound of the Weiss-Weinstein family. Among this family, we have Bayesian Cram{\'e}r-Rao bound, the Bobrovsky-MayerWolf-Zaka{\"i} bound, the Bayesian Bhattacharyya bound, the Bobrovsky-Zaka{\"i} bound, the Reuven-Messer bound, and the Weiss-Weinstein bound. We present a unification of all these minimal bounds based on a rewriting of the minimum mean square error estimator (MMSEE) and on a constrained optimization problem. With this approach, we obtain a useful theoretical framework to derive new Bayesian bounds. For that purpose, we propose two bounds. First, we propose a generalization of the Bayesian Bhattacharyya bound extending the works of Bobrovsky, Mayer-Wolf, and Zaka{\"i}. Second, we propose a bound based on the Bayesian Bhattacharyya bound and on the Reuven-Messer bound, representing a generalization of these bounds. The proposed bound is the Bayesian extension of the deterministic Abel bound and is found to be tighter than the Bayesian Bhattacharyya bound, the Reuven-Messer bound, the Bobrovsky-Zaka{\"i} bound, and the Bayesian Cram{\'e}r-Rao bound. We propose some closed-form expressions of these bounds for a general Gaussian observation model with parameterized mean. In order to illustrate our results, we present simulation results in the context of a spectral analysis problem.",
keywords = "Bayesian bounds on the MSE, Weiss-Weinstein family",
author = "Alexandre Renaux and Philippe Forster and Pascal Larzabal and Christ Richmond and Arye Nehorai",
year = "2008",
month = "11",
day = "3",
doi = "10.1109/TSP.2008.927075",
language = "English (US)",
volume = "56",
pages = "5334--5352",
journal = "IEEE Transactions on Signal Processing",
issn = "1053-587X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

TY - JOUR

T1 - A fresh look at the Bayesian bounds of the Weiss-Weinstein family

AU - Renaux, Alexandre

AU - Forster, Philippe

AU - Larzabal, Pascal

AU - Richmond, Christ

AU - Nehorai, Arye

PY - 2008/11/3

Y1 - 2008/11/3

N2 - Minimal bounds on the mean square error (MSE) are generally used in order to predict the best achievable performance of an estimator for a given observation model. In this paper, we are interested in the Bayesian bound of the Weiss-Weinstein family. Among this family, we have Bayesian Cramér-Rao bound, the Bobrovsky-MayerWolf-Zakaï bound, the Bayesian Bhattacharyya bound, the Bobrovsky-Zakaï bound, the Reuven-Messer bound, and the Weiss-Weinstein bound. We present a unification of all these minimal bounds based on a rewriting of the minimum mean square error estimator (MMSEE) and on a constrained optimization problem. With this approach, we obtain a useful theoretical framework to derive new Bayesian bounds. For that purpose, we propose two bounds. First, we propose a generalization of the Bayesian Bhattacharyya bound extending the works of Bobrovsky, Mayer-Wolf, and Zakaï. Second, we propose a bound based on the Bayesian Bhattacharyya bound and on the Reuven-Messer bound, representing a generalization of these bounds. The proposed bound is the Bayesian extension of the deterministic Abel bound and is found to be tighter than the Bayesian Bhattacharyya bound, the Reuven-Messer bound, the Bobrovsky-Zakaï bound, and the Bayesian Cramér-Rao bound. We propose some closed-form expressions of these bounds for a general Gaussian observation model with parameterized mean. In order to illustrate our results, we present simulation results in the context of a spectral analysis problem.

AB - Minimal bounds on the mean square error (MSE) are generally used in order to predict the best achievable performance of an estimator for a given observation model. In this paper, we are interested in the Bayesian bound of the Weiss-Weinstein family. Among this family, we have Bayesian Cramér-Rao bound, the Bobrovsky-MayerWolf-Zakaï bound, the Bayesian Bhattacharyya bound, the Bobrovsky-Zakaï bound, the Reuven-Messer bound, and the Weiss-Weinstein bound. We present a unification of all these minimal bounds based on a rewriting of the minimum mean square error estimator (MMSEE) and on a constrained optimization problem. With this approach, we obtain a useful theoretical framework to derive new Bayesian bounds. For that purpose, we propose two bounds. First, we propose a generalization of the Bayesian Bhattacharyya bound extending the works of Bobrovsky, Mayer-Wolf, and Zakaï. Second, we propose a bound based on the Bayesian Bhattacharyya bound and on the Reuven-Messer bound, representing a generalization of these bounds. The proposed bound is the Bayesian extension of the deterministic Abel bound and is found to be tighter than the Bayesian Bhattacharyya bound, the Reuven-Messer bound, the Bobrovsky-Zakaï bound, and the Bayesian Cramér-Rao bound. We propose some closed-form expressions of these bounds for a general Gaussian observation model with parameterized mean. In order to illustrate our results, we present simulation results in the context of a spectral analysis problem.

KW - Bayesian bounds on the MSE

KW - Weiss-Weinstein family

UR - http://www.scopus.com/inward/record.url?scp=54949113694&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=54949113694&partnerID=8YFLogxK

U2 - 10.1109/TSP.2008.927075

DO - 10.1109/TSP.2008.927075

M3 - Article

AN - SCOPUS:54949113694

VL - 56

SP - 5334

EP - 5352

JO - IEEE Transactions on Signal Processing

JF - IEEE Transactions on Signal Processing

SN - 1053-587X

IS - 11

ER -