Singular vector and singular subspace distribution for the matrix denoising model

DOI10.1214/20-AOS1960zbMath1459.60011arXiv1809.10476OpenAlexW3127939736MaRDI QIDQ2656600

Yanyan Li

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/1809.10476

zbMATH Keywords

random matrixsingular vectorsingular subspacenonuniversalitysignal-plus-noise modelmatrix denoising model

Mathematics Subject Classification ID

Multivariate distribution of statistics (62H10) Factor analysis and principal components; correspondence analysis (62H25) Nonparametric hypothesis testing (62G10) Random matrices (probabilistic aspects) (60B20) Random matrices (algebraic aspects) (15B52)

Related Items

Asymptotic Theory of Eigenvectors for Random Matrices With Diverging Spikes ⋮ Statistical inference for principal components of spiked covariance matrices ⋮ Inference for low-rank tensors -- no need to debias ⋮ Uncovering block structures in large rectangular matrices ⋮ Eigen Selection in Spectral Clustering: A Theory-Guided Practice ⋮ Unnamed Item ⋮ Universal rank inference via residual subsampling with application to large networks ⋮ Tracy-Widom law for the extreme eigenvalues of large signal-plus-noise matrices ⋮ The limiting spectral distribution of large-dimensional general information-plus-noise-type matrices ⋮ Spiked multiplicative random matrices and principal components ⋮ Learning low-dimensional nonlinear structures from high-dimensional noisy data: an integral operator approach ⋮ Rapid evaluation of the spectral signal detection threshold and Stieltjes transform ⋮ Normal approximation and confidence region of singular subspaces ⋮ Matrix Denoising for Weighted Loss Functions and Heterogeneous Signals ⋮ Eigenvector distribution in the critical regime of BBP transition ⋮ Edge statistics of large dimensional deformed rectangular matrices

Cites Work

• Unnamed Item
• Limits of spiked random matrices. II
• Limits of spiked random matrices. I
• Averaging fluctuations in resolvents of random band matrices
• Fluctuations of the extreme eigenvalues of finite rank deformations of random matrices
• The singular values and vectors of low rank perturbations of large rectangular random matrices
• The outliers of a deformed Wigner matrix
• Minimax risk of matrix denoising by singular value thresholding
• Asymptotics and concentration bounds for bilinear forms of spectral projectors of sample covariance
• Normal approximation and concentration of spectral projectors of sample covariance
• The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices
• Anisotropic local laws for random matrices
• Central limit theorems for eigenvalues in a spiked population model
• On sample eigenvalues in a generalized spiked population model
• 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
• Spectral analysis of large dimensional random matrices
• Local law and Tracy-Widom limit for sparse random matrices
• Random perturbation of low rank matrices: improving classical bounds
• Canonical correlation coefficients of high-dimensional Gaussian vectors: finite rank case
• Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics
• A subspace estimator for fixed rank perturbations of large random matrices
• On finite rank deformations of Wigner matrices
• Efficient estimation of linear functionals of principal components
• High dimensional deformed rectangular matrices with applications in matrix denoising
• The two-to-infinity norm and singular subspace geometry with applications to high-dimensional statistics
• Universality for the largest eigenvalue of sample covariance matrices with general population
• Tracy-Widom limit for the largest eigenvalue of a large class of complex sample covariance matrices
• Central limit theorems for eigenvalues of deformations of Wigner matrices
• Isotropic local laws for sample covariance and generalized Wigner matrices
• Universality of covariance matrices
• The largest eigenvalue of rank one deformation of large Wigner matrices
• Eigenvalues of large sample covariance matrices of spiked population models
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• On the principal components of sample covariance matrices
• The Isotropic Semicircle Law and Deformation of Wigner Matrices
• Biclustering via Sparse Singular Value Decomposition
• Rate Optimal Denoising of Simultaneously Sparse and Low Rank Matrices
• An $\ell_{\infty}$ Eigenvector Perturbation Bound and Its Application to Robust Covariance Estimation
• Spectrum of deformed random matrices and free probability
• Dimensionality-reduced subspace clustering
• The Role of Principal Angles in Subspace Classification
• Near-Optimal Bounds for Phase Synchronization
• Limiting Eigenvectors of Outliers for Spiked Information-Plus-Noise Type Matrices
• Confidence Region of Singular Subspaces for Low-Rank Matrix Regression
• Asymptotic Theory for Principal Component Analysis
• Signal-plus-noise matrix models: eigenvector deviations and fluctuations