inria-00444732, version 1
A Cramer-Rao Bound Characterization of the EM-Algorithm Mean Speed of Convergence
IEEE Transactions on Signal Processing 56, 6 (2008) 2218-2228
Abstract: This paper deals with the mean speed of convergence of the expectation-maximization (EM) algorithm. We show that the asymptotic behavior (in terms of the number of observations) of the EM algorithm can be characterized as a function of the Cramér-Rao bounds (CRBs) associated to the so-called incomplete and complete data sets defined within the EM-algorithm framework. We particularize our result to the case of a complete data set defined as the concatenation of the observation vector and a vector of nuisance parameters, independent of the parameter of interest. In this particular case, we show that the CRB associated to the complete data set is nothing but the well-known modified CRB. Finally, we show by simulation that the proposed expression enables to properly characterize the EM-algorithm mean speed of convergence from the CRB behavior when the size of the observation set is large enough.
- a – INRIA
- b – Université de Paris-Sud Orsay
- c – Université Catholique de Louvain
- 1:
- CNRS : UMR6074 – INRIA – Université de Rennes 1
- 2:
- Université Catholique de Louvain (UCL) - Belgique
- 3:
- UMR8506 CNRS – SUPELEC – Université Paris XI - Paris Sud
- Domain : Computer Science/Signal and Image Processing
Engineering Sciences/Signal and Image processing - Keywords : Convergence of numerical methods – iterative methods – maximum-likelihood estimation
- inria-00444732, version 1
- http://hal.inria.fr/inria-00444732
- oai:hal.inria.fr:inria-00444732
- From:
- Submitted on: Thursday, 7 January 2010 11:32:22
- Updated on: Monday, 11 January 2010 12:52:59




Associated documents
Export