From Poincaré Inequalities to Nonlinear Matrix Concentration

Abstract

This paper deduces exponential matrix concentration from a Poincaré inequality via a short, conceptual argument. Among other examples, this theory applies to matrix-valued functions of a uniformly log-concave random vector. The proof relies on the subadditivity of Poincaré inequalities and a chain rule inequality for the trace of the matrix Dirichlet form. It also uses a symmetrization technique to avoid difficulties associated with a direct extension of the classic scalar argument.

References in corpus (5)

• Concentration of the adjacency matrix and of the Laplacian in random graphs with independent edges
• Quantum logarithmic Sobolev inequalities and rapid mixing
• On the joint convexity of the Bregman divergence of matrices
• Subadditivity of Matrix phi-Entropy and Concentration of Random Matrices
• Nonlinear Matrix Concentration via Semigroup Methods

Cited by in corpus (1)

• Nonlinear Matrix Concentration via Semigroup Methods