Which Graphical Models Are Difficult to Learn?
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).
Cite
Text
Montanari and Pereira. "Which Graphical Models Are Difficult to Learn?." Neural Information Processing Systems, 2009.Markdown
[Montanari and Pereira. "Which Graphical Models Are Difficult to Learn?." Neural Information Processing Systems, 2009.](https://mlanthology.org/neurips/2009/montanari2009neurips-graphical/)BibTeX
@inproceedings{montanari2009neurips-graphical,
title = {{Which Graphical Models Are Difficult to Learn?}},
author = {Montanari, Andrea and Pereira, Jose A.},
booktitle = {Neural Information Processing Systems},
year = {2009},
pages = {1303-1311},
url = {https://mlanthology.org/neurips/2009/montanari2009neurips-graphical/}
}