Which graphical models are difficult to learn?
Machine Learning
2009-11-07 v1 Statistical Mechanics
Machine Learning
Abstract
We consider the problem of learning the structure of Ising models (pairwise binary Markov random fields) from i.i.d. samples. While several methods have been proposed to accomplish this task, their relative merits and limitations remain somewhat obscure. By analyzing a number of concrete examples, we show that low-complexity algorithms systematically fail when the Markov random field develops long-range correlations. More precisely, this phenomenon appears to be related to the Ising model phase transition (although it does not coincide with it).
Keywords
Cite
@article{arxiv.0910.5761,
title = {Which graphical models are difficult to learn?},
author = {Jose Bento and Andrea Montanari},
journal= {arXiv preprint arXiv:0910.5761},
year = {2009}
}