Matrix Concentration Inequalities and Free Probability

Abstract

A central tool in the study of nonhomogeneous random matrices, the noncommutative Khintchine inequality, yields a nonasymptotic bound on the spectral norm of general Gaussian random matrices $X={\sum }_i{g}_i{A}_i$ where $g_i$ are independent standard Gaussian variables and $A_i$ are matrix coefficients. This bound exhibits a logarithmic dependence on dimension that is sharp when the matrices $A_i$ commute, but often proves to be suboptimal in the presence of noncommutativity. In this paper, we develop nonasymptotic bounds on the spectrum of arbitrary Gaussian random matrices that can capture noncommutativity. These bounds quantify the degree to which the spectrum of $X$ is captured by that of a noncommutative model $X_{\mathrm{free}}$ that arises from free probability theory. This "intrinsic freeness" phenomenon provides a powerful tool for the study of various questions that are outside the reach of classical methods of random matrix theory. Our nonasymptotic bounds are easily applicable in concrete situations, and yield sharp results in examples where the noncommutative Khintchine inequality is suboptimal. When combined with a linearization argument, our bounds imply strong asymptotic freeness for a remarkably general class of Gaussian random matrix models that may be very sparse, have dependent entries, and lack any special symmetries. When combined with a universality principle, our bounds extend beyond the Gaussian setting to general sums of independent random matrices.

56 pages

References in corpus (1)

• Strong asymptotic freeness for independent uniform variables on compact groups associated to non-trivial representations

Cited by in corpus (13)

• Optimal Embedding Dimension for Sparse Subspace Embeddings
• Consequences of the random matrix solution to the Peterson-Thom conjecture
• Chevet-type inequalities for subexponential Weibull variables and estimates for norms of random matrices
• Extreme singular values of inhomogeneous sparse random rectangular matrices
• A note on quantum expanders
• Quantum Glassiness From Efficient Learning
• Norm of matrix-valued polynomials in random unitaries and permutations
• Low-Rank Toeplitz Matrix Restoration: Descent Cone Analysis and Structured Random Matrix
• Optimal quantum (tensor product) expanders from unitary designs
• Sharp concentration for sums of matrices with Markovian dependence through universality
• Spectral measure of large random Helson matrices
• Kronecker-product random matrices and a matrix least squares problem
• Finite rank perturbation of non-Hermitian random matrices: heavy tail and sparse regimes