Matrix concentration inequalities via the method of exchangeable pairs
From MaRDI portal
Publication:2450243
Abstract: This paper derives exponential concentration inequalities and polynomial moment inequalities for the spectral norm of a random matrix. The analysis requires a matrix extension of the scalar concentration theory developed by Sourav Chatterjee using Stein's method of exchangeable pairs. When applied to a sum of independent random matrices, this approach yields matrix generalizations of the classical inequalities due to Hoeffding, Bernstein, Khintchine and Rosenthal. The same technique delivers bounds for sums of dependent random matrices and more general matrix-valued functions of dependent random variables.
Recommendations
Cites work
- A Combinatorial Central Limit Theorem
- A simpler approach to matrix completion
- Compressive sensing and structured random matrices
- Convex trace functions and the Wigner-Yanase-Dyson conjecture
- Derandomizing the Ahlswede-Winter matrix-valued Chernoff bound using pessimistic estimators, and applications
- Distribution function inequalities for martingales
- Freedman's inequality for matrix martingales
- Functions of Matrices
- scientific article; zbMATH DE number 4170917 (Why is no real title available?)
- scientific article; zbMATH DE number 3951374 (Why is no real title available?)
- scientific article; zbMATH DE number 3589464 (Why is no real title available?)
- scientific article; zbMATH DE number 647292 (Why is no real title available?)
- scientific article; zbMATH DE number 3438144 (Why is no real title available?)
- scientific article; zbMATH DE number 1849957 (Why is no real title available?)
- scientific article; zbMATH DE number 967931 (Why is no real title available?)
- Matrix probing and its conditioning
- Moment inequalities for sums of random matrices and their applications in optimization
- Non commutative Khintchine and Paley inequalities
- Non-commutative martingale inequalities
- Noncommutative Burkholder/Rosenthal inequalities
- Noncommutative Burkholder/Rosenthal inequalities. II: Applications
- On the stability and accuracy of least squares approximations
- On the subspaces of \(L^p\) \((p > 2)\) spanned by sequences of independent random variables
- Operator Khintchine inequality in non-commutative probability
- Optimum bounds for the distributions of martingales in Banach spaces
- Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
- Probability Inequalities for Sums of Bounded Random Variables
- Random vectors in the isotropic position
- Recovering Low-Rank Matrices From Few Coefficients in Any Basis
- Restricted strong convexity and weighted matrix completion: optimal bounds with noise
- Sampling from large matrices
- Stein's method for concentration inequalities
- Strong converse for identification via quantum channels
- Sublinear randomized algorithms for skeleton decompositions
- Sums of random Hermitian matrices and an inequality by Rudelson
- Tail inequalities for sums of random matrices that depend on the intrinsic dimension
- The concentration of measure phenomenon
- The masked sample covariance estimator: an analysis using matrix concentration inequalities
- Trace inequalities and quantum entropy: an introductory course
- User-friendly tail bounds for sums of random matrices
Cited in
(56)- Sigma delta quantization with harmonic frames and partial Fourier ensembles
- Distribution of singular values of random band matrices; Marchenko-Pastur law and more
- Near-optimality of linear recovery from indirect observations
- Second-order matrix concentration inequalities
- Estimation from nonlinear observations via convex programming with application to bilinear regression
- Approximate kernel partial least squares
- From Poincaré inequalities to nonlinear matrix concentration
- Nonlinear matrix concentration via semigroup methods
- Upper and lower bounds for matrix discrepancy
- Wasserstein-based methods for convergence complexity analysis of MCMC with applications
- Time-uniform Chernoff bounds via nonnegative supermartingales
- Central moment inequalities using Stein's method
- Moment inequalities for matrix-valued U-statistics of order 2
- Concentration inequalities for random matrix products
- Weighted Poincaré inequalities, concentration inequalities and tail bounds related to Stein kernels in dimension one
- Stein's method, logarithmic Sobolev and transport inequalities
- Restricted isometry property of principal component pursuit with reduced linear measurements
- Noncommutative Bennett and Rosenthal inequalities
- Riemannian stochastic variance-reduced cubic regularized Newton method for submanifold optimization
- A general parametric Stein characterization
- Bernstein-type inequality for a class of dependent random matrices
- Product mixing in the alternating group
- The expected norm of a sum of independent random matrices: an elementary approach
- Impact of regularization on spectral clustering
- Efron-Stein inequalities for random matrices
- Tail inequalities for sums of random matrices that depend on the intrinsic dimension
- A Stein characterisation of the generalized hyperbolic distribution
- On computationally tractable selection of experiments in measurement-constrained regression models
- Matching component analysis for transfer learning
- On expected error of randomized Nyström kernel regression
- Stochastic variance-reduced cubic regularization methods
- A matrix expander Chernoff bound
- LSV-based tail inequalities for sums of random matrices
- Pipage rounding, pessimistic estimators and matrix concentration
- An introduction to matrix concentration inequalities
- Concentration and moment inequalities for polynomials of independent random variables
- Randomized numerical linear algebra: Foundations and algorithms
- Spherical random sampling of localized functions on 𝕊ⁿ⁻¹
- Subsampling spectral clustering for stochastic block models in large-scale networks
- Matrix anti-concentration inequalities with applications
- Concentration inequalities for the spectral measure of random matrices
- On the functional regression model and its finite-dimensional approximations
- Universality and sharp matrix concentration inequalities
- Relevant sampling in finitely generated shift-invariant spaces
- Max-norm optimization for robust matrix recovery
- Concentration inequalities for matrix martingales in continuous time
- Matrix Freedman inequality for sub-Weibull martingales
- User-friendly tail bounds for sums of random matrices
- Central limit theorem for Gram-Schmidt random walk design
- Concentration inequalities for sums of Markov-dependent random matrices
- Randomized low-rank approximations beyond Gaussian random matrices
- Sums of squares certificates for polynomial moment inequalities
- Sharp concentration for sums of matrices with Markovian dependence through universality
- Stein's method for the matrix normal distribution
- Matrix Poincaré inequalities and concentration
- Stein's method for nonlinear statistics: a brief survey and recent progress
This page was built for publication: Matrix concentration inequalities via the method of exchangeable pairs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2450243)
