User-Friendly Tail Bounds for Sums of Random Matrices

This work presents probability inequalities for sums of independent, random, self-adjoint matrices. The results frame simple, easily verifiable hypotheses on the summands, and they yield strong conclusions about the large-deviation behavior of the maximum eigenvalue of the sum. Tail bounds for the norm of a sum of rectangular matrices follow as an immediate corollary, and similar techniques yield information about matrix-valued martingales. In other words, this paper provides noncommutative generalizations of the classical bounds associated with the names Azuma, Bennett, Bernstein, Chernoff, Hoeffding, and McDiarmid. The matrix inequalities promise the same ease of use, diversity of application, and strength of conclusion that have made the scalar inequalities so valuable.