Abstract: We consider the problem of learning the structure of Ising models (pairwise binary Markov random fields) from iid 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.
Andrea Montanari hasn't uploaded this paper.
Let Andrea know you want this paper to be uploaded.
