Ali Jalali, Christopher Johnson, and Pradeep Ravikumar
In this paper, we address the problem of learning the structure of a pairwise graphical model from samples in a high-dimensional setting. Our first main result studies the sparsistency, or consistency in sparsity pattern recovery, properties of a forward-backward greedy algorithm as applied to general statistical models. As a special case, we then apply this algorithm to learn the structure of a discrete graphical model via neighborhood estimation. As a corollary of our general result, we derive sufficient conditions on the number of samplesn, the maximum nodedegree d and the problem size p, as well as other conditions on the model parameters, so that the algorithm recovers all the edges with high probability. Our result guarantees graph selection for samples scaling as n = O(d 2 log(p)), in contrast to existing convex-optimization based algorithms that require a sample complexity of O(d 3 log(p)). Further, the greedy algorithm only requires a restricted strong convexity condition which is typically milder than irrepresentability assumptions. We corroborate these results using numerical simulations at the end.
In Neural Information Processing Systems 2011.

Pradeep Ravikumar Faculty pradeepr [at] cs utexas edu