2000 character limit reached
Efron-Stein Inequalities for Random Matrices (1408.3470v1)
Published 15 Aug 2014 in math.PR and math.FA
Abstract: This paper establishes new concentration inequalities for random matrices constructed from independent random variables. These results are analogous with the generalized Efron-Stein inequalities developed by Boucheron et al. The proofs rely on the method of exchangeable pairs.