Kullback Proximal Algorithms for Maximum Likelihood Estimation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 1999

Kullback Proximal Algorithms for Maximum Likelihood Estimation


In this paper, we study the convergence of a new class of fast and stable sequential optimization methods for computing maximum likelihood estimates. These methods are based on a proximal point algorithm implemented with a Kullback-type proximal function. When the proximal regularization parameter is set to unity one obtains the classical expectation maximization (EM) algorithm. For other values of the regularization parameter, relaxed versions of EM are obtained which can have much faster convergence. In particular, if the regularization parameter vanishes at infinity, a superlinearly converging algorithm is obtained. We present an implementation of the algorithm using the trust region update strategy. For illustration the method is applied to a non-quadratic inverse problem with Poisson distributed data.
Fichier principal
Vignette du fichier
RR-3756.pdf (296.55 Ko) Télécharger le fichier

Dates and versions

inria-00072906 , version 1 (24-05-2006)


  • HAL Id : inria-00072906 , version 1


Stéphane Chrétien, Alfred O. Hero. Kullback Proximal Algorithms for Maximum Likelihood Estimation. [Research Report] RR-3756, INRIA. 1999. ⟨inria-00072906⟩
81 View
12588 Download


Gmail Facebook Twitter LinkedIn More