Robust Gaussian Covariance Estimation in
       Nearly-Matrix Multiplication Time

           Jerry Li                  Guanghao Ye
         Microsoft Research             University of Washington
        jerrl@microsoft.com                ghye@uw.edu

                       Abstract
     Robust covariance estimation is the following, well-studied problem in high di-
     mensional statistics: given N samples from a d-dimensional Gaussian N (0, Σ),
     but where an ε-fraction of the samples hav ...