Tail inequalities for sums of random matrices that depend on the intrinsic dimension

DOI10.1214/ECP.v17-1869zbMath1243.60007arXiv1104.1672OpenAlexW2164899006MaRDI QIDQ428742

Sham M. Kakade, Daniel Hsu, Tong Zhang

Publication date: 22 June 2012

Published in: Electronic Communications in Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1104.1672

zbMATH Keywords

large deviationintrinsic dimensionrandom matrix

Mathematics Subject Classification ID

Random matrices (probabilistic aspects) (60B20) Large deviations (60F10)

Related Items

Integer LWE with non-subgaussian error and related attacks, Dimension-free bounds for largest singular values of matrix Gaussian series, On some extensions of Bernstein's inequality for self-adjoint operators, Sparse Hanson-Wright inequalities for subgaussian quadratic forms, Random design analysis of ridge regression, LSV-Based Tail Inequalities for Sums of Random Matrices, Matrix concentration inequalities via the method of exchangeable pairs, Fast Randomized Algorithms for t-Product Based Tensor Operations and Decompositions with Applications to Imaging Data, Randomized Approximation of the Gram Matrix: Exact Computation and Probabilistic Bounds, Small-deviation inequalities for sums of random matrices, Bootstrapping the operator norm in high dimensions: error estimation for covariance matrices and sketching