Matrix Concentration Inequalities via the Method of Exchangeable Pairs

This paper derives exponential concentration inequalities and polynomial moment inequalities for the spectral norm of a random matrix. The analysis requires a matrix extension of the scalar concentration theory developed by Sourav Chatterjee using Stein’s method of exchangeable pairs. When applied to a sum of independent random matrices, this approach yields matrix generalizations of the classical inequalities due to Hoeffding, Bernstein, Khintchine, and Rosenthal. The same technique delivers bounds for sums of dependent random matrices and more general matrix-valued functions of dependent random variables.

PDF

Authors: Lester Mackey, Michael Jordan, Richard Y. Chen, Brendan Farrell, Joel A. Tropp
Publication Date: January 2012
Conference: Annals of Probability