Universality and Sharp Matrix Concentration Inequalities

By Tatiana Brailovskaya, Ramon van Handel. Geometric and Functional Analysis, 2022

67 citations recorded by the source corpus.

We show that, under mild assumptions, the spectrum of a sum of independent random matrices is close to that of the Gaussian random matrix whose entries have the same mean and covariance. This nonasymptotic universality principle yields sharp matrix concentration inequalities for general sums of independent random matrices when combined with the Gaussian theory of Bandeira, Boedihardjo, and Van Handel. A key feature of the resulting theory is that it is applicable to a broad class of random matrix models that may have highly nonhomogeneous and dependent entries, which can be far outside the mean-field situation considered in classical random matrix theory. We illustrate the theory in applications to random graphs, matrix concentration inequalities for smallest singular values, sample covariance matrices, strong asymptotic freeness, and phase transitions in spiked models.

Subfields: Discrete Mathematics and Combinatorics, Geometry and Topology, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/2fd5eb446ab7c5d4154749f0579750d351607907

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Discrete Mathematics and Combinatorics

In Geometry and Topology

In Statistics and Probability

Citations in the corpus

Matrix concentration inequalities and free probability (2021, background): “From a broader viewpoint, the results of the present paper and of [10] suggest that the study of a broad class of random matrices can be separated into two largely independent problems: a universality principle, which shows that a nonGaussian and Gaussian model behave alike; and the “intrinsic freen”