Dynamics of the maximum marginal likelihood hyper-parameter estimation in image restoration : gradient descent vs. EM algorithm
Disordered Systems and Neural Networks
2009-11-07 v2
Abstract
Dynamical properties of image restoration and hyper-parameter estimation are investigated by means of statistical mechanics. We introduce an exactly solvable model for image restoration and derive differential equations with respect to macroscopic quantities. From these equations, we evaluate relaxation processes of the system to the equilibrium state. Our statistical mechanical approach also enable us to investigate the hyper-parameter estimation by means of maximization of marginal likelihood by using gradient decent and EM algorithm from dynamical point of view.
Cite
@article{arxiv.cond-mat/0107023,
title = {Dynamics of the maximum marginal likelihood hyper-parameter estimation in image restoration : gradient descent vs. EM algorithm},
author = {Jun-ichi Inoue and Kazuyuki Tanaka},
journal= {arXiv preprint arXiv:cond-mat/0107023},
year = {2009}
}
Comments
latex 22 pages using revtex, 6 ps figures