Abstract: In this paper we consider the task of estimating the non-zero pattern of the sparse inverse covariance matrix of a zero-mean Gaussian random vector from a set of iid samples. Note that this is also equivalent to recovering the underlying graph structure of a sparse Gaussian Markov Random Field (GMRF). We present two novel greedy approaches to solving this problem. The first estimates the non-zero covariates of the overall inverse covariance matrix using a series of global forward and backward greedy steps. The second estimates the neighborhood of each node in the graph separately, again using greedy forward and backward steps, and combines the intermediate neighborhoods to form an overall estimate. The principal contribution of this paper is a rigorous analysis of the sparsistency of these two greedy procedures, that is, their consistency in recovering the sparsity pattern of the inverse covariance matrix. Surprisingly, we show that both the local and global greedy methods learn the full structure of the model with high probability given just O(dlog(p)) samples, which is a significant improvement over state of the art l1-regularized Gaussian MLE (Graphical Lasso) that requires O(d2 log(p)) samples. Moreover, the restricted eigenvalue and smoothness conditions imposed by our greedy methods are much weaker than the strong irrepresentable conditions required by the l1-regularization based methods. We corroborate our results with extensive simulations and examples, comparing our local and global greedy methods to the l1-regularized Gaussian MLE as well as the node-wise l1regularized linear regression (Neighborhood Lasso).
- High-dimensional Sparse Inverse Covariance Estimation using Greedy Methods (pdf, software)
A. Jalali, C. Johnson, P. Ravikumar.
In International Conference on Artificial Intelligence and Statistics (AISTATS), 2012.