Model Selection Through Sparse Maximum Likelihood Estimation
TITLE: Model Selection Through Sparse Maximum Likelihood Estimation.
AUTHORS: Onureena Banerjee, Laurent El Ghaoui, Alexandre d'Aspremont
ABSTRACT: We consider the problem of estimating the parameters of a Gaussian or binary distribution in such a way that the resulting undirected graphical model is sparse. Our approach is to solve a maximum likelihood problem with an added l_1norm penalty term. The problem as formulated is convex but the memory requirements and complexity of existing interior point methods are prohibitive for problems with more than tens of nodes. We present two new algorithms for solving problems with at least a thousand nodes in the Gaussian case. Our first algorithm uses block coordinate descent, and can be interpreted as recursive l_1norm penalized regression. Our second algorithm, based on Nesterov's first order method, yields a complexity estimate with a better dependence on problem size than existing interior point methods. Using a log determinant relaxation of the log partition function (Wainwright and Jordan (2006)), we show that these same algorithms can be used to solve an approximate sparse maximum likelihood problem for the binary case. We test our algorithms on synthetic data, as well as on gene expression and senate voting records data.
STATUS: Journal of Machine Learning Research, 9, pp. 485516, March 2008.
ArXiv PREPRINT: 0707.0704
PAPER: Model Selection Through Sparse Maximum Likelihood Estimation in pdf
