Asymmetry helps: eigenvalue and eigenvector analyses of asymmetrically perturbed low-rank matrices

DOI10.1214/20-AOS1963zbMath1461.62085arXiv1811.12804OpenAlexW3128401515MaRDI QIDQ2656603

Yuxin Chen, Chen Cheng, Jianqing Fan

Publication date: 11 March 2021

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1811.12804

zbMATH Keywords

heteroscedasticityspectral methodseigenvalue perturbationentrywise eigenvector perturbationlinear form of eigenvectors

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Estimation in multivariate analysis (62H12) Inference from stochastic processes and spectral analysis (62M15) Eigenvalues, singular values, and eigenvectors (15A18)

Related Items

Detection thresholds in very sparse matrix completion, Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval, Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization, Normal approximation and confidence region of singular subspaces, Subspace estimation from unbalanced and incomplete data matrices: \({\ell_{2,\infty}}\) statistical guarantees

Cites Work

• Unnamed Item
• Outliers in the single ring theorem
• Spectral statistics of Erdős-Rényi graphs. I: Local semicircle law
• Erratum to: Outliers in the spectrum of iid matrices with bounded rank perturbations
• The singular values and vectors of low rank perturbations of large rectangular random matrices
• The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices
• Central limit theorems for eigenvalues in a spiked population model
• Eigenvectors of random matrices: A survey
• Norms and exclusion theorems
• The largest eigenvalue of small rank perturbations of Hermitian random matrices
• The largest eigenvalues of finite rank deformation of large Wigner matrices: Convergence and nonuniversality of the fluctuations
• On the limit of the largest eigenvalue of the large dimensional sample covariance matrix
• The eigenvalues of random symmetric matrices
• Non-hermitian random matrix theory: Method of hermitian reduction
• Non-Hermitean delocalization: multiple scattering and bounds
• Random perturbation of low rank matrices: improving classical bounds
• Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics
• On the distribution of the largest eigenvalue in principal components analysis
• On delocalization of eigenvectors of random non-Hermitian matrices
• Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution
• Limiting laws for divergent spiked eigenvalues and largest nonspiked eigenvalue of sample covariance matrices
• Entrywise eigenvector analysis of random matrices with low expected rank
• Spectral method and regularized MLE are both optimal for top-\(K\) ranking
• Rapid, robust, and reliable blind deconvolution via nonconvex optimization
• The largest eigenvalue of rank one deformation of large Wigner matrices
• Eigenvalues of large sample covariance matrices of spiked population models
• Exact matrix completion via convex optimization
• Outlier Eigenvalues for Deformed I.I.D. Random Matrices
• The Isotropic Semicircle Law and Deformation of Wigner Matrices
• Perturbation of Linear Forms of Singular Vectors Under Gaussian Noise
• Random weighted projections, random quadratic forms and random eigenvectors
• Large-Neigenvalue distribution of randomly perturbed asymmetric matrices
• The spectral radii and norms of large dimensional non-central random atrices matrices
• An $\ell_{\infty}$ Eigenvector Perturbation Bound and Its Application to Robust Covariance Estimation
• Tensor SVD: Statistical and Computational Limits
• ON FINITE RANK DEFORMATIONS OF WIGNER MATRICES II: DELOCALIZED PERTURBATIONS
• Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization
• Confidence Region of Singular Subspaces for Low-Rank Matrix Regression
• Inference and uncertainty quantification for noisy matrix completion
• Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
• Singular Vector Perturbation Under Gaussian Noise
• On Consistency and Sparsity for Principal Components Analysis in High Dimensions
• Matrix Completion From a Few Entries
• Singular vectors under random perturbation
• An Introduction to Matrix Concentration Inequalities
• The Rotation of Eigenvectors by a Perturbation. III
• Perturbation bounds in connection with singular value decomposition
• Signal-plus-noise matrix models: eigenvector deviations and fluctuations