On the trade-off between complexity and correlation decay in structural learning algorithms
Machine Learning
2011-10-11 v1 Machine Learning
Data Analysis, Statistics and Probability
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 often 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.1110.1769,
title = {On the trade-off between complexity and correlation decay in structural learning algorithms},
author = {José Bento and Andrea Montanari},
journal= {arXiv preprint arXiv:1110.1769},
year = {2011}
}