On regularization methods of EM-Kaczmarz type
Numerical Analysis
2015-05-13 v1
Abstract
We consider regularization methods of Kaczmarz type in connection with the expectation-maximization (EM) algorithm for solving ill-posed equations. For noisy data, our methods are stabilized extensions of the well established ordered-subsets expectation-maximization iteration (OS-EM). We show monotonicity properties of the methods and present a numerical experiment which indicates that the extended OS-EM methods we propose are much faster than the standard EM algorithm.
Keywords
Cite
@article{arxiv.0810.3619,
title = {On regularization methods of EM-Kaczmarz type},
author = {Markus Haltmeier and Antonio Leitao and Elena Resmerita},
journal= {arXiv preprint arXiv:0810.3619},
year = {2015}
}
Comments
18 pages, 6 figures; On regularization methods of EM-Kaczmarz type