Poster
Which graphical models are difficult to learn?
Andrea Montanari · José Bento

Mon Dec 7th 07:00 -- 11:59 PM @ None #None

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).

Author Information

Andrea Montanari (Stanford)
José Bento (Boston College)

More from the Same Authors