Robust covariance estimation under norm equivalence

Abstract
Let be a centered random vector taking values in and let be its covariance matrix. We show that if satisfies an norm equivalence, there is a covariance estimator that exhibits the optimal performance one would expect had been a gaussian vector. The procedure also improves the current state-of-the-art regarding high probability bounds in the subgaussian case (sharp results were only known in expectation or with constant probability). In both scenarios the new bound does not depend explicitly on the dimension , but rather on the effective rank of the covariance matrix .
View on arXivComments on this paper