An optimal rotational invariant estimator for general covariance matrices​

par Antti Knowles

jeudi 3 mars 2016, 14:00 → 15:00 Europe/Paris

salle 435 (UMPA)

We consider sample covariance matrices in the high-dimensional regime where the number of variables is comparable to the number of samples. The underlying population covariance matrix is allowed to be very general and include outliers. We prove that there exists a consistent, unified, and optimal rotational invariant estimator of the population covariance matrix that depends only on observable quantities. All results hold at a local scale of individual eigenvalues, with optimal large deviation error bounds. Joint work with J. Bun and J. Yin.