Matrix concentration inequalities via the method of exchangeable pairs
نویسندگان
چکیده
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. This paper is based on two independent manuscripts from mid-2011 that both applied the method of exchangeable pairs to establish matrix concentration inequalities. One manuscript is by Mackey and Jordan; the other is by Chen, Farrell, and Tropp. The authors have combined this research into a single unified presentation, with equal contributions from both groups.
منابع مشابه
Matrix Concentration Inequalities via the Method of Exchangeable Pairs1 by Lester Mackey2,
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 classi...
متن کاملDeriving Matrix Concentration Inequalities from Kernel Couplings
This paper derives exponential tail bounds and polynomial moment inequalities for the spectral norm deviation of a random matrix from its mean value. The argument depends on a matrix extension of Stein's method of exchangeable pairs for concentration of measure, as introduced by Chatterjee. Recent work of Mackey et al. uses these techniques to analyze random matrices with additive structure, wh...
متن کاملEfron–Stein Inequalities for Random Matrices
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. AMS 2000 subject classifications: Primary 60B20, 60E15; secondary 60G09, 60F10.
متن کاملMatrix Factorization and Matrix Concentration
Matrix Factorization and Matrix Concentration by Lester Wayne Mackey II Doctor of Philosophy in Electrical Engineering and Computer Sciences with the Designated Emphasis in Communication, Computation, and Statistics University of California, Berkeley Professor Michael I. Jordan, Chair Motivated by the constrained factorization problems of sparse principal components analysis (PCA) for gene expr...
متن کاملRandom Subgraph Countsand U -statistics: Multivariate Normal Approximation via Exchangeable Pairs and Embedding
In Reinert and Röllin (2009) a new approach—called the ‘embedding method’—was introduced, which allows us tomake use of exchangeable pairs for normal andmultivariate normal approximations with Stein’s method in cases where the corresponding couplings do not satisfy a certain linearity condition. The key idea is to embed the problem into a higher-dimensional space in such a way that the linearit...
متن کامل