A refined non-asymptotic tail bound of sub-Gaussian matrix

DOI10.3770/J.ISSN:2095-2651.2020.05.010zbMATH Open1463.15023arXiv1906.10432MaRDI QIDQ3385957FDOQ3385957

Chao Zhang, Xianjie Gao, Hongwei Zhang

Publication date: 14 January 2021

Abstract: In this paper, we obtain a refined non-asymptotic tail bound for the largest singular value (the soft edge) of sub-Gaussian matrix. As an application, we use the obtained theorem to compute the tail bound of the Gaussian Toeplitz matrix.

Full work available at URL: https://arxiv.org/abs/1906.10432

Recommendations

• Upper bound for intermediate singular values of random matrices
• User-friendly tail bounds for sums of random matrices
• Smallest singular value of a random rectangular matrix
• Sharp nonasymptotic bounds on the norm of random matrices with independent entries
• A tail inequality for quadratic forms of subgaussian random vectors

zbMATH Keywords

largest singular valuetail boundnon-asymptotic theorysub-Gaussian matrix

Mathematics Subject Classification ID

Eigenvalues, singular values, and eigenvectors (15A18) Inequalities involving eigenvalues and eigenvectors (15A42) Random matrices (algebraic aspects) (15B52) Random matrices (probabilistic aspects) (60B20)

Cited In (2)

• Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries
• Sub-stochastic matrix analysis for bounds computation -- theoretical results

This page was built for publication: A refined non-asymptotic tail bound of sub-Gaussian matrix

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3385957)