Quantitative estimates of the convergence of the empirical covariance matrix in log-concave ensembles

DOI10.1090/S0894-0347-09-00650-XzbMath1206.60006arXiv0903.2323WikidataQ105583999 ScholiaQ105583999MaRDI QIDQ3584355

Radosław Adamczak, Alain Pajor, Nicole Tomczak-Jaegermann, Alexander E. Litvak

Publication date: 27 August 2010

Published in: Journal of the American Mathematical Society (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/0903.2323

zbMATH Keywords

convex bodies isotropic measures log-concave measures sample covariance matrices

Mathematics Subject Classification ID

Inequalities; stochastic orderings (60E15) Random matrices (probabilistic aspects) (60B20) Probabilistic methods in Banach space theory (46B09) Convexity and finite-dimensional Banach spaces (including special norms, zonoids, etc.) (aspects of convex geometry) (52A21)

Related Items (64)

Condition number of a square matrix with i.i.d. columns drawn from a convex body ⋮ Random matrices, geometric functional analysis and algorithms. Abstracts from the workshop held May 1--7, 2011. ⋮ Coverings of random ellipsoids, and invertibility of matrices with i.i.d. heavy-tailed entries ⋮ Random embeddings with an almost Gaussian distortion ⋮ Gaussian and robust Kronecker product covariance estimation: existence and uniqueness ⋮ An isomorphic Dvoretzky-Milman theorem using general random ensembles ⋮ A practical volume algorithm ⋮ On the interval of fluctuation of the singular values of random matrices ⋮ Sampling discretization and related problems ⋮ Non-asymptotic properties of spectral decomposition of large Gram-type matrices and applications ⋮ Concentration phenomena in high dimensional geometry ⋮ The smallest singular value of random rectangular matrices with no moment assumptions on entries ⋮ Almost sure convergence of the largest and smallest eigenvalues of high-dimensional sample correlation matrices ⋮ On the geometry of polytopes generated by heavy-tailed random vectors ⋮ The lower tail of random quadratic forms with applications to ordinary least squares ⋮ Bayesian inference for spectral projectors of the covariance matrix ⋮ Empirical processes with a bounded $\psi_1$ diameter ⋮ Covariance estimation for distributions with ${2+\varepsilon}$ moments ⋮ Pairwise sparse + low-rank models for variables of mixed type ⋮ On the convergence of the extremal eigenvalues of empirical covariance matrices with dependence ⋮ Folded concave penalized sparse linear regression: sparsity, statistical performance, and algorithmic theory for local solutions ⋮ Limiting spectral distribution for a type of sample covariance matrices ⋮ Convergence of the largest eigenvalue of normalized sample covariance matrices when $p$ and $n$ both tend to infinity with their ratio converging to zero ⋮ On a multi-integral norm defined by weighted sums of log-concave random vectors ⋮ Phase transitions for support recovery under local differential privacy ⋮ Sharp bounds on the rate of convergence of the empirical covariance matrix ⋮ On generic chaining and the smallest singular value of random matrices with heavy tails ⋮ Side effects of learning from low-dimensional data embedded in a Euclidean space ⋮ Dimension-free bounds for sums of independent matrices and simple tensors via the variational principle ⋮ Dimension-free bounds for sums of dependent matrices and operators with heavy-tailed distributions ⋮ Worst-Case Convergence Analysis of Inexact Gradient and Newton Methods Through Semidefinite Programming Performance Estimation ⋮ Restricted isometry property of matrices with independent columns and neighborly polytopes by random sampling ⋮ Approximating the covariance ellipsoid ⋮ Quermaßintegrals and asymptotic shape of random polytopes in an isotropic convex body ⋮ Geometry of log-concave ensembles of random matrices and approximate reconstruction ⋮ Small-ball probabilities for the volume of random convex sets ⋮ On the isotropic constant of random polytopes ⋮ Estimating covariance and precision matrices along subspaces ⋮ Restricted isometry property for random matrices with heavy-tailed columns ⋮ Phase retrieval: stability and recovery guarantees ⋮ Random tensor theory: Extending random matrix theory to mixtures of random product states ⋮ Log-concavity and strong log-concavity: a review ⋮ On higher order isotropy conditions and lower bounds for sparse quadratic forms ⋮ The smallest singular value of a shifted $d$-regular random square matrix ⋮ The limit of the smallest singular value of random matrices with i.i.d. entries ⋮ Row products of random matrices ⋮ How close is the sample covariance matrix to the actual covariance matrix? ⋮ Approximating the moments of marginals of high-dimensional distributions ⋮ Spectral norm of products of random and deterministic matrices ⋮ Random polytopes generated by contoured distributions ⋮ An upper bound on the smallest singular value of a square random matrix ⋮ Rank-one multi-reference factor analysis ⋮ Asymptotic shape of a random polytope in a convex body ⋮ High-dimensional nonparametric density estimation via symmetry and shape constraints ⋮ Non-asymptotic results for singular values of Gaussian matrix products ⋮ Marcinkiewicz-type discretization of $L^p$-norms under the Nikolskii-type inequality assumption ⋮ Beyond covariance: SICE and kernel based visual feature representation ⋮ On Monte-Carlo methods in convex stochastic optimization ⋮ Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices ⋮ Quantitative Version of a Silverstein’s Result ⋮ An efficiency upper bound for inverse covariance estimation ⋮ Covariance estimation under one-bit quantization ⋮ Asymptotic shape of the convex hull of isotropic log-concave random vectors ⋮ Variable metric random pursuit

Cites Work

This page was built for publication: Quantitative estimates of the convergence of the empirical covariance matrix in log-concave ensembles