Sharp nonasymptotic bounds on the norm of random matrices with independent entries

DOI10.1214/15-AOP1025zbMath1372.60004arXiv1408.6185OpenAlexW1553284371MaRDI QIDQ317469

Afonso S. Bandeira, Ramon van Handel

Publication date: 30 September 2016

Published in: The Annals of Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1408.6185

zbMATH Keywords

random matricesspectral normnon-asymptotic boundstail inequalities

Mathematics Subject Classification ID

Random matrices (probabilistic aspects) (60B20) Large deviations (60F10) Probabilistic methods in Banach space theory (46B09)

Related Items

On the non-asymptotic concentration of heteroskedastic Wishart-type matrix, CLT for non-Hermitian random band matrices with variance profiles, On the Expectation of Operator Norms of Random Matrices, Density and spacings for the energy levels of quadratic Fermi operators, Lower bounds for the smallest singular value of structured random matrices, Model-free Nonconvex Matrix Completion: Local Minima Analysis and Applications in Memory-efficient Kernel PCA, Singularity of sparse Bernoulli matrices, The dimension-free structure of nonhomogeneous random matrices, Random sections of ellipsoids and the power of random information, Markov random geometric graph, MRGG: a growth model for temporal dynamic networks, Sparse and smooth: improved guarantees for spectral clustering in the dynamic stochastic block model, A Hoeffding inequality for Markov chains, A UNIFORM BOUND ON THE OPERATOR NORM OF SUB-GAUSSIAN RANDOM MATRICES AND ITS APPLICATIONS, An extension of the angular synchronization problem to the heterogeneous setting, Unnamed Item, Concentration of the spectral norm of Erdős-Rényi random graphs, A simple spectral algorithm for recovering planted partitions, Joint Community Detection and Rotational Synchronization via Semidefinite Programming, Norms of random matrices: local and global problems, Scalable subspace methods for derivative-free nonlinear least-squares optimization, Direct Search Based on Probabilistic Descent in Reduced Spaces, Matrix concentration inequalities and free probability, Fluctuations in mean-field Ising models, A unified approach to synchronization problems over subgroups of the orthogonal group, Approximate message passing for sparse matrices with application to the equilibria of large ecological Lotka-Volterra systems, A localization-delocalization transition for nonhomogeneous random matrices, Unnamed Item, Norms of structured random matrices, Bias-Adjusted Spectral Clustering in Multi-Layer Stochastic Block Models, Random geometric graph: some recent developments and perspectives, Spectral Clustering via Adaptive Layer Aggregation for Multi-Layer Networks, On the distance to low-rank matrices in the maximum norm, Applied harmonic analysis and data science. Abstracts from the workshop held November 28 -- December 4, 2021 (hybrid meeting), On the spectral norm of Gaussian random matrices, Finding Planted Subgraphs with Few Eigenvalues using the Schur--Horn Relaxation, Adaptive confidence sets for matrix completion, Spectral radii of sparse random matrices, Unnamed Item, Unnamed Item, Unnamed Item, Random Laplacian matrices and convex relaxations, Invertibility of sparse non-Hermitian matrices, Tightness of the maximum likelihood semidefinite relaxation for angular synchronization, Low-rank model with covariates for count data with missing values, Sharp transition of the invertibility of the adjacency matrices of sparse random graphs, Two-sample Hypothesis Testing for Inhomogeneous Random Graphs, Adaptive estimation of nonparametric geometric graphs, Convex relaxation methods for community detection, Circular law for random block band matrices with genuinely sublinear bandwidth, Convex optimization for the densest subgraph and densest submatrix problems, Sparse random tensors: concentration, regularization and applications, Optimal graphon estimation in cut distance, The spectral norm of random lifts of matrices, Exact Clustering of Weighted Graphs via Semidefinite Programming, Analysis of spectral clustering algorithms for community detection: the general bipartite setting, Structured matrix estimation and completion, Constructive regularization of the random matrix norm, Unnamed Item, Large deviations for the largest eigenvalue of Gaussian networks with constant average degree, Feasibility of sparse large Lotka-Volterra ecosystems, Linear eigenvalue statistics of random matrices with a variance profile, Relative perturbation bounds with applications to empirical covariance operators

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the expectation of the norm of random matrices with non-identically distributed entries
• The spectral edge of some random band matrices
• Sums of random Hermitian matrices and an inequality by Rudelson
• User-friendly tail bounds for sums of random matrices
• Largest eigenvalues and eigenvectors of band or sparse random matrices
• Lifts, discrepancy and nearly optimal spectral gap
• The Tracy-Widom law for some sparse random matrices
• Necessary and sufficient conditions for almost sure convergence of the largest eigenvalue of a Wigner matrix
• A limit theorem for the norm of random matrices
• The eigenvalues of random symmetric matrices
• Moment inequalities for functions of independent random variables
• About the constants in Talagrand's concentration inequalities for empirical processes.
• Non-asymptotic theory of random matrices: extreme singular values
• Sampling convex bodies: a random matrix approach
• An Introduction to Random Matrices
• The Expected Norm of Random Matrices
• Some estimates of norms of random matrices
• Upper and Lower Bounds for Stochastic Processes