Small-deviation inequalities for sums of random matrices

DOI10.3390/SYM11050638MaRDI QIDQ2338012zbMATH OpenOpenAlexWikidataFDO

Authors Xianjie Gao, Chao Zhang, Hongwei Zhang

Publication date 20 November 2019

Published in Symmetry (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/1810.07334

zbMATH Keywords

large-deviation inequalitylargest singular valuerandom matrixsmall-deviation inequality

Mathematics Subject Classification ID

Inequalities involving eigenvalues and eigenvectors (15A42) Random matrices (algebraic aspects) (15B52)

Abstract: Random matrices have played an important role in many fields including machine learning, quantum information theory and optimization. One of the main research focuses is on the deviation inequalities for eigenvalues of random matrices. Although there are intensive studies on the large-deviation inequalities for random matrices, only a few of works discuss the small-deviation behavior of random matrices. In this paper, we present the small-deviation inequalities for the largest eigenvalues of sums of random matrices. Since the resulting inequalities are independent of the matrix dimension, they are applicable to the high-dimensional and even the infinite-dimensional cases.

Review text

Summary: Random matrices have played an important role in many fields including machine learning, quantum information theory, and optimization. One of the main research focuses is on the deviation inequalities for eigenvalues of random matrices. Although there are intensive studies on the large-deviation inequalities for random matrices, only a few works discuss the small-deviation behavior of random matrices. In this paper, we present the small-deviation inequalities for the largest eigenvalues of sums of random matrices. Since the resulting inequalities are independent of the matrix dimension, they are applicable to high-dimensional and even the infinite-dimensional cases.

Recommendations

• User-friendly tail bounds for sums of random matrices
• Tail inequalities for sums of random matrices that depend on the intrinsic dimension
• Deviation Inequalities on Largest Eigenvalues
• Efron-Stein inequalities for random matrices
• Recent developments in non-asymptotic theory of random matrices

Cites work

• Approximation, metric entropy and small ball estimates for Gaussian measures
• Capture time of Brownian pursuits
• Deviation Inequalities on Largest Eigenvalues
• Eigenvalues and Condition Numbers of Random Matrices
• Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions
• scientific article; zbMATH DE number 2149892 (Why is no real title available?)
• Invertibility of symmetric random matrices
• LSV-based tail inequalities for sums of random matrices
• Non-asymptotic theory of random matrices: extreme singular values
• On some extensions of Bernstein's inequality for self-adjoint operators
• On the link between small ball probabilities and the quantization problem for Gaussian measures on Banach spaces
• Revisiting the Nyström method for improved large-scale machine learning
• Small ball probability and Dvoretzky's Theorem
• Small deviations of the determinants of random matrices with Gaussian entries
• Statistics for high-dimensional data. Methods, theory and applications.
• Strong converse for identification via quantum channels
• Tail inequalities for sums of random matrices that depend on the intrinsic dimension
• The convex geometry of linear inverse problems
• The Littlewood-Offord problem and invertibility of random matrices
• User-friendly tail bounds for sums of random matrices

Cited in

(4)

• Small deviations of the determinants of random matrices with Gaussian entries
• Tail inequalities for sums of random matrices that depend on the intrinsic dimension
• Dimension-free bounds for sums of independent matrices and simple tensors via the variational principle
• Sums of random Hermitian matrices and an inequality by Rudelson

This page was built for publication: Small-deviation inequalities for sums of random matrices

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2338012)