ECE Seminar: Robust Subspace Modeling
Friday, March 22, 2013 - 11:45am to 1:00pm
Gilad Lerman, Ph.D., Associate Professor, School of Mathematics, University of Minnesota
Robust Subspace Modeling Consider a dataset of vector-valued observations that consists of a modest number of noisy inliers, which are explained well by a low-dimensional subspace, along with a large number of outliers, which have no linear structure. We describe a convex optimization problem that can reliably fit a low-dimensional model to this type of data. When the inliers are contained in a low-dimensional subspace we provide a rigorous theory that describes when this optimization can recover the subspace exactly. We present an efficient algorithm for solving this optimization problem, whose computational cost is comparable to that of the non-truncated SVD. We also show that the sample complexity of the proposed subspace recovery is of the same order as PCA subspace recovery and we consequently obtain some nontrivial robustness to noise. This presentation is based on three joint works: 1) with Teng Zhang, 2) with Michael McCoy, Joel Tropp and Teng Zhang, and 3) with Matthew Coudron. Dr. Gilad Lerman is an Associate Professor in the School of Mathematics at the University of Minnesota. He received his Ph.D. degree in Mathematics from Yale University in 2000 and then worked as a postdoc/Courant Instructor at NYU before moving to Minnesota. His present research interests include high-dimensional data analysis and modeling, computational harmonic analysis, machine learning and computer vision. He is a recipient of the NSF Career Award.