A tail inequality for quadratic forms of subgaussian random vectors

DOI10.1214/ECP.V17-2079zbMATH Open1309.60017arXiv1110.2842OpenAlexW2052044664WikidataQ105584381 ScholiaQ105584381MaRDI QIDQ742954FDOQ742954

Authors: Daniel Hsu, Sham M. Kakade, Tong Zhang 

Publication date: 22 September 2014

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

Abstract: We prove an exponential probability tail inequality for positive semidefinite quadratic forms in a subgaussian random vector. The bound is analogous to one that holds when the vector has independent Gaussian entries.

Full work available at URL: https://arxiv.org/abs/1110.2842

Recommendations

• Bounds on tail probabilities for quadratic forms in dependent sub-Gaussian random variables
• Asymptotic behavior of tails and quantiles of quadratic forms of Gaussian vectors.
• scientific article; zbMATH DE number 32965
• Inequalities for the distributions of functionals of sub-Gaussian vectors
• Estimates for tail probabilities of bilinear forms in negatively dependent subgaussian random variables
• Bounds on the tail probability of 𝑈-statistics and quadratic forms
• Tail probability of a noncentral indefinite gaussian quadratic form
• Two properties of vectors of quadratic forms in Gaussian random variables

zbMATH Keywords

quadratic formssub-Gaussian random vectorstail inequality

Mathematics Subject Classification ID

Large deviations (60F10)

Cited In (75)

• Random vectors satisfying Khinchine–Kahane type inequalities for linear and quadratic forms
• An Interactive Greedy Approach to Group Sparsity in High Dimensions
• Research and application of Hoeffding inequality under sub-Gaussian distribution
• Some notes on concentration for \(\alpha\)-subexponential random variables
• Probability and moment inequalities for additive functionals of geometrically ergodic Markov chains
• Title not available (Why is that?)
• Dimension-free bounds for sums of independent matrices and simple tensors via the variational principle
• Adaptive and robust multi-task learning
• Inference in a Class of Optimization Problems: Confidence Regions and Finite Sample Bounds on Errors in Coverage Probabilities
• Title not available (Why is that?)
• Fully polynomial-time randomized approximation schemes for global optimization of high-dimensional minimax concave penalized generalized linear models
• Nonasymptotic one- and two-sample tests in high dimension with unknown covariance structure
• Fast convex pruning of deep neural networks
• High-resolution signal recovery via generalized sampling and functional principal component analysis
• Change-point detection in high-dimensional covariance structure
• Modified log-Sobolev inequalities and two-level concentration
• Finite-sample analysis of \(M\)-estimators using self-concordance
• Provably secure NTRU instances over prime cyclotomic rings
• Nonclassical Berry-Esseen inequalities and accuracy of the bootstrap
• Uniform Hanson-Wright type concentration inequalities for unbounded entries via the entropy method
• Compressed dictionary learning
• On principal components regression, random projections, and column subsampling
• Optimal signal detection in some spiked random matrix models: likelihood ratio tests and linear spectral statistics
• Structured matrix estimation and completion
• Title not available (Why is that?)
• Variance-based extragradient methods with line search for stochastic variational inequalities
• On the optimization landscape of tensor decompositions
• Fluctuation of the free energy of Sherrington-Kirkpatrick model with Curie-Weiss interaction: the paramagnetic regime
• Minimax nonparametric estimation on maxisets
• Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution
• Covariate regularized community detection in sparse graphs
• Posterior contraction in group sparse logit models for categorical responses
• Finite sample performance of linear least squares estimation
• The likelihood ratio test in high-dimensional logistic regression is asymptotically a rescaled Chi-square
• Folded concave penalized sparse linear regression: sparsity, statistical performance, and algorithmic theory for local solutions
• Title not available (Why is that?)
• Prediction and estimation consistency of sparse multi-class penalized optimal scoring
• Variable selection for partially linear models via Bayesian subset modeling with diffusing prior
• Bayesian linear regression for multivariate responses under group sparsity
• Fast nonasymptotic testing and support recovery for large sparse Toeplitz covariance matrices
• SONIC: social network analysis with influencers and communities
• Random design analysis of ridge regression
• A refined non-asymptotic tail bound of sub-Gaussian matrix
• Inference without compatibility: using exponential weighting for inference on a parameter of a linear model
• Concentration inequalities for bounded functionals via log-Sobolev-type inequalities
• Concentration inequalities for polynomials in \(\alpha\)-sub-exponential random variables
• Log-concave sampling: Metropolis-Hastings algorithms are fast
• Policy space identification in configurable environments
• Title not available (Why is that?)
• Bounds on tail probabilities for quadratic forms in dependent sub-Gaussian random variables
• Statistical inference for Bures-Wasserstein barycenters
• Adaptive function-on-scalar regression with a smoothing elastic net
• Title not available (Why is that?)
• Neyman-Pearson classification: parametrics and sample size requirement
• The lower tail of random quadratic forms with applications to ordinary least squares
• Hanson-Wright inequality in Hilbert spaces with application to \(K\)-means clustering for non-Euclidean data
• Achieving the oracle property of OEM with nonconvex penalties
• High-dimensional Bayesian inference in nonparametric additive models
• Estimates for tail probabilities of bilinear forms in negatively dependent subgaussian random variables
• Sharp deviation bounds for quadratic forms
• On asymptotically minimax nonparametric detection of signal in Gaussian white noise
• Bayesian variable selection with shrinking and diffusing priors
• A unified approach to synchronization problems over subgroups of the orthogonal group
• Concentration inequalities for statistical inference
• On concentration inequalities for vector-valued Lipschitz functions
• Why Are Big Data Matrices Approximately Low Rank?
• Random weighted projections, random quadratic forms and random eigenvectors
• Sparse Hanson-Wright inequalities for subgaussian quadratic forms
• Heterogeneity adjustment with applications to graphical model inference
• Linear regression with sparsely permuted data
• Derivative-free methods for policy optimization: guarantees for linear quadratic systems
• Title not available (Why is that?)
• Sharp optimal recovery in the two component Gaussian mixture model
• Sparse quadratic classification rules via linear dimension reduction
• Optimal variable selection in multi-group sparse discriminant analysis

This page was built for publication: A tail inequality for quadratic forms of subgaussian random vectors

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q742954)