Constrained MMSE Estimator for Distribution Mismatch Compensation

Author

Lederman, Dror ; Tabrikian, Joseph

Author_Institution

Dept. of Electr. & Comput. Eng., Ben-Gurion Univ. of the Negev, Beer-Sheva

fYear

2006

fDate

12-14 July 2006

Firstpage

439

Lastpage

443

Abstract

This paper addresses the problem of Bayesian estimation in the presence of signal distribution mismatch. A new estimator is derived based on the minimum mean-square error (MMSE) criterion with constraints on the first and second order statistics of the parameters of interest. The resulting constrained MMSE (CMMSE) estimator is found to be robust to signal distribution mismatch, since it incorporates statistical information on the parameters of interest. The performance of the CMMSE estimator under different mismatch conditions is studied via simulations using several examples. It is shown that the CMMSE estimator outperforms the MMSE in the presence of signal distribution mismatch. With no distribution mismatch, the CMMSE performance is slightly lower than the MMSE

Keywords

Bayes methods; least mean squares methods; signal processing; Bayesian estimation; constrained MMSE estimator; distribution mismatch compensation; minimum mean-square error; signal distribution mismatch; Bayesian methods; Covariance matrix; Degradation; Error analysis; Minimax techniques; Minimization methods; Robustness; Statistical distributions; Statistics; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Sensor Array and Multichannel Processing, 2006. Fourth IEEE Workshop on

Conference_Location

Waltham, MA

Print_ISBN

1-4244-0308-1

Type

conf

DOI

10.1109/SAM.2006.1706171

Filename

1706171