The spectral norm of Gaussian matrices with correlated entries

2021/04/06 by Afonso S. Bandeira, March T. Boedihardjo, Bandeira, Afonso S. +1 · 1 citation
Mathematics · #Random Matrices and Applications #Advanced Combinatorial Mathematics #Graph theory and applications

paper · pdf · doi:10.48550/arxiv.2104.02662

Abstract

We give a non-asymptotic bound on the spectral norm of a d× d matrix X with centered jointly Gaussian entries in terms of the covariance matrix of the entries. In some cases, this estimate is sharp and removes the √(log d) factor in the noncommutative Khintchine inequality.

Cited by

• Reconcile Certified Robustness and Accuracy for DNN-based Smoothed Majority Vote Classifier

Related

• Tail Bounds on the Spectral Norm of Sub-Exponential Random Matrices
• On the Smallest Eigenvalue of General correlated Gaussian Matrices
• On Spectral Norm of Large Band Random Matrices
• On the concentration of Gaussian Cayley matrices
• CLT for LES of correlated Non-Hermitian Random Matrices