A note on the Hanson-Wright inequality for random vectors with dependencies

DOI10.1214/ECP.V20-3829zbMATH Open1328.60050arXiv1409.8457MaRDI QIDQ894498FDOQ894498

Radosław Adamczak

Publication date: 1 December 2015

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

Abstract: We prove that quadratic forms in isotropic random vectors $X$ in $mathbb{R}^n$, possessing the convex concentration property with constant $K$, satisfy the Hanson-Wright inequality with constant $CK$, where $C$ is an absolute constant, thus eliminating the logarithmic (in the dimension) factors in a recent estimate by Vu and Wang. We also show that the concentration inequality for all Lipschitz functions implies a uniform version of the Hanson-Wright inequality for suprema of quadratic forms (in the spirit of the inequalities by Borell, Arcones-Gin'e and Ledoux-Talagrand). Previous results of this type relied on stronger isoperimetric properties of $X$ and in some cases provided an upper bound on the deviations rather than a concentration inequality. In the last part of the paper we show that the uniform version of the Hanson-Wright inequality for Gaussian vectors can be used to recover a recent concentration inequality for empirical estimators of the covariance operator of $B$-valued Gaussian variables due to Koltchinskii and Lounici.

Full work available at URL: https://arxiv.org/abs/1409.8457

Recommendations

• Hanson-Wright inequality and sub-Gaussian concentration
• Hanson-Wright inequality in Banach spaces
• Uniform Hanson-Wright type concentration inequalities for unbounded entries via the entropy method
• Sparse Hanson-Wright inequalities for subgaussian quadratic forms
• The Hanson-Wright inequality for random tensors

zbMATH Keywords

quadratic formsconcentration of measureHanson-Wright inequalityempirical covariance operator

Mathematics Subject Classification ID

Probability theory on linear topological spaces (60B11) Inequalities; stochastic orderings (60E15)

Cited In (30)

• Concentration inequalities on the multislice and for sampling without replacement
• Estimation of binary time-frequency masks from ambient noise
• New challenges in covariance estimation: multiple structures and coarse quantization
• Modified log-Sobolev inequalities and two-level concentration
• Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon
• Norms of sub-exponential random vectors
• Concentration of kernel matrices with application to kernel spectral clustering
• Moments of Gaussian chaoses in Banach spaces
• Uniform Hanson-Wright type concentration inequalities for unbounded entries via the entropy method
• Relative perturbation bounds with applications to empirical covariance operators
• Some notes on concentration for \(\alpha\)-subexponential random variables
• Controlling the least eigenvalue of a random Gram matrix
• Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks
• A note on concentration for polynomials in the Ising model
• High-dimensional limit of one-pass SGD on least squares
• Variance reduction for Markov chains with application to MCMC
• Hanson-Wright inequality in Banach spaces
• Variations and extensions of the Gaussian concentration inequality, Part I
• Tyler's and Maronna's M-estimators: non-asymptotic concentration results
• Dimension-free bounds for sums of independent matrices and simple tensors via the variational principle
• Covariance Model with General Linear Structure and Divergent Parameters
• Concentration inequalities for bounded functionals via log-Sobolev-type inequalities
• Concentration inequalities for polynomials in \(\alpha\)-sub-exponential random variables
• Bounds on tail probabilities for quadratic forms in dependent sub-Gaussian random variables
• Hanson-Wright inequality in Hilbert spaces with application to \(K\)-means clustering for non-Euclidean data
• Generic error bounds for the generalized Lasso with sub-exponential data
• Random Euclidean embeddings in finite-dimensional Lorentz spaces
• Perturbation bounds for eigenspaces under a relative gap condition
• Provable training set debugging for linear regression
• Spectral-norm risk rates for multi-taper estimation of Gaussian processes

This page was built for publication: A note on the Hanson-Wright inequality for random vectors with dependencies

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q894498)