Title :
A connection between half-quadratic criteria and EM algorithms
Author :
Champagnat, Frédéric ; Idier, Jérôme
Author_Institution :
Office Nat. d´´Etudes et de Recherches Aerospatiales, Chatillon, France
Abstract :
Iteratively Reweighted Least Squares (IRLS) and Residual Steepest descent (RSD) algorithms of robust statistics arise as special cases of half-quadratic schemes . Here, we adopt a statistical framework and we show that both algorithms are instances of the EM algorithm. The augmented dataset respectively involves a scale and a location mixture of Gaussians. The sufficient conditions for the construction cover a broad class of already known robust statistics.
Keywords :
image restoration; iterative methods; least squares approximations; quadratic programming; EM algorithm; IRLS; RSD; half-quadratic scheme; iteratively reweighted least squares; residual steepest descent algorithm; Bayesian methods; Equations; Gaussian processes; Image restoration; Iterative algorithms; Least squares methods; Robustness; Signal processing algorithms; Statistics; Sufficient conditions; EM algorithm; IRLS; RSD; half-quadratic criteria; iteratively reweighted least squares; residual steepest descent; scale mixtures;
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2004.833511
