Optimal cleaning for singular values of cross-covariance matrices

Abstract
We give a new algorithm for the estimation of the cross-covariance matrix of two large dimensional signals , in the context where the number of observations of the pair is large but and are not supposed to be small. In the asymptotic regime where are large, with high probability, this algorithm is optimal for the Frobenius norm among rotationally invariant estimators, i.e. estimators derived from the empirical estimator by cleaning the singular values, while letting singular vectors unchanged.
View on arXivComments on this paper