Hanson-Wright inequality and sub-Gaussian concentration
From MaRDI portal
(Redirected from Publication:743056)
Abstract: In this expository note, we give a modern proof of Hanson-Wright inequality for quadratic forms in sub-gaussian random variables. We deduce a useful concentration inequality for sub-gaussian random vectors. Two examples are given to illustrate these results: a concentration of distances between random vectors and subspaces, and a bound on the norms of products of random and deterministic matrices.
Recommendations
- Sparse Hanson-Wright inequalities for subgaussian quadratic forms
- Hanson-Wright inequality in Banach spaces
- A note on the Hanson-Wright inequality for random vectors with dependencies
- Concentration inequalities for polynomials in \(\alpha\)-sub-exponential random variables
- Uniform Hanson-Wright type concentration inequalities for unbounded entries via the entropy method
Cited in
(only showing first 100 items - show all)- A sequence of triangle-free pseudorandom graphs
- Strong selection consistency of Bayesian vector autoregressive models based on a pseudo-likelihood approach
- Sparse principal component analysis for high‐dimensional stationary time series
- Clustering multivariate count data via Dirichlet-multinomial network fusion
- On Dvoretzky's theorem for subspaces of \(L_p\)
- Model selection for high-dimensional linear regression with dependent observations
- A robust bootstrap change point test for high-dimensional location parameter
- On binary embedding using circulant matrices
- Estimation of binary time-frequency masks from ambient noise
- On the asymptotic behavior of the eigenvalue distribution of block correlation matrices of high-dimensional time series
- Learning particle swarming models from data with Gaussian processes
- Convergence of covariance and spectral density estimates for high-dimensional locally stationary processes
- Guaranteed Functional Tensor Singular Value Decomposition
- Norms of sub-exponential random vectors
- Complex phase retrieval from subgaussian measurements
- Modified log-Sobolev inequalities and two-level concentration
- On the asymptotic distribution of the maximum sample spectral coherence of Gaussian time series in the high dimensional regime
- Matrix denoising for weighted loss functions and heterogeneous signals
- Fixed-Domain Posterior Contraction Rates for Spatial Gaussian Process Model with Nugget
- IFF: A Superresolution Algorithm for Multiple Measurements
- Uniform Hanson-Wright type concentration inequalities for unbounded entries via the entropy method
- Lifting for blind deconvolution in random mask imaging: identifiability and convex relaxation
- On the volume of non-central sections of a cube
- Mass equidistribution for random polynomials
- Lasso guarantees for \(\beta \)-mixing heavy-tailed time series
- An autocovariance-based learning framework for high-dimensional functional time series
- Some notes on concentration for \(\alpha\)-subexponential random variables
- High-Dimensional Analysis of Double Descent for Linear Regression with Random Projections
- Posterior graph selection and estimation consistency for high-dimensional Bayesian DAG models
- A bootstrap method for error estimation in randomized matrix multiplication
- On the asymptotic variance of the debiased Lasso
- Comparison and anti-concentration bounds for maxima of Gaussian random vectors
- Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution
- The Hanson-Wright inequality for random tensors
- The likelihood ratio test in high-dimensional logistic regression is asymptotically a rescaled Chi-square
- Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks
- Spectrahedral Regression
- Asymptotics for high dimensional regression \(M\)-estimates: fixed design results
- Subspace perspective on canonical correlation analysis: dimension reduction and minimax rates
- Quantization and compressive sensing
- Higher order concentration on Stiefel and Grassmann manifolds
- Testing for high-dimensional network parameters in auto-regressive models
- Finite sample theory for high-dimensional functional/scalar time series with applications
- Penalized estimation of threshold auto-regressive models with many components and thresholds
- A note on the Hanson-Wright inequality for random vectors with dependencies
- Strong consistency guarantees for clustering high-dimensional bipartite graphs with the spectral method
- Regularized estimation and testing for high-dimensional multi-block vector-autoregressive models
- Optimal bounds for aggregation of affine estimators
- Kernel spectral clustering of large dimensional data
- Consistent Bayesian sparsity selection for high-dimensional Gaussian DAG models with multiplicative and beta-mixture priors
- On the smoothed analysis of the smallest singular value with discrete noise
- Noise-shaping quantization methods for frame-based and compressive sampling systems
- Concentration of the collision estimator
- Fast nonasymptotic testing and support recovery for large sparse Toeplitz covariance matrices
- An exponential rarefaction result for sub-Gaussian real algebraic maximal curves
- Hanson-Wright inequality in Banach spaces
- Estimating high-dimensional covariance and precision matrices under general missing dependence
- On delocalization of eigenvectors of random non-Hermitian matrices
- Eigenvectors of random matrices: A survey
- Minimax rate-optimal estimation of high-dimensional covariance matrices with incomplete data
- On the consistency of inversion-free parameter estimation for Gaussian random fields
- Analysis of sparse MIMO radar
- Concentration of measure bounds for matrix-variate data with missing values
- Upper bound for intermediate singular values of random matrices
- Resonances for random highly oscillatory potentials
- A random matrix approach to neural networks
- Tyler's and Maronna's M-estimators: non-asymptotic concentration results
- Error guarantees for least squares approximation with noisy samples in domain adaptation
- A large deviation inequality for the rank of a random matrix
- Nonlinear wavelet-based estimation to spectral density for stationary non-Gaussian linear processes
- A note on moment inequality for quadratic forms
- Finite impulse response models: a non-asymptotic analysis of the least squares estimator
- Concentration inequalities for bounded functionals via log-Sobolev-type inequalities
- Concentration inequalities for polynomials in \(\alpha\)-sub-exponential random variables
- A class of dimension-free metrics for the convergence of empirical measures
- Spectral graph matching and regularized quadratic relaxations. I: Algorithm and Gaussian analysis
- Spectral graph matching and regularized quadratic relaxations. II: Erdős-Rényi graphs and universality
- A stochastic perturbation analysis of the QR decomposition and its applications
- Marchenko–Pastur law with relaxed independence conditions
- Circular law for sparse random regular digraphs
- A theoretical perspective on hyperdimensional computing
- Estimation of low-rank covariance function
- scientific article; zbMATH DE number 7626737 (Why is no real title available?)
- Concentration inequalities for random tensors
- Bounds on tail probabilities for quadratic forms in dependent sub-Gaussian random variables
- Delocalization of eigenvectors of random matrices with independent entries
- A machine learning approach to optimal Tikhonov regularization. I: Affine manifolds
- Performance analysis of local ensemble Kalman filter
- Regularized estimation in sparse high-dimensional time series models
- Gibbs measures associated to the integrals of motion of the periodic derivative nonlinear Schrödinger equation
- Fluctuations of quadratic chaos
- Nonparametric spectral density estimation under local differential privacy
- Structured random sketching for PDE inverse problems
- Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions: continuous dynamics
- Fermionic eigenvector moment flow
- A two-stage penalized least squares method for constructing large systems of structural equations
- Limiting spectral distribution of renormalized separable sample covariance matrices when \(p/n\to 0\)
- Sharp Analysis of Sketch-and-Project Methods via a Connection to Randomized Singular Value Decomposition
- On the distance to low-rank matrices in the maximum norm
- Perturbation upper bounds for singular subspaces with a kind of heteroskedastic noise and its application in clustering
This page was built for publication: Hanson-Wright inequality and sub-Gaussian concentration
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q743056)
