The two-to-infinity norm and singular subspace geometry with applications to high-dimensional statistics

DOI10.1214/18-AOS1752zbMath1470.62065arXiv1705.10735OpenAlexW2966291568WikidataQ114060556 ScholiaQ114060556MaRDI QIDQ2328047

Joshua Cape, Minh Tang, Carey E. Priebe

Publication date: 9 October 2019

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

Full work available at URL: https://arxiv.org/abs/1705.10735

zbMATH Keywords

singular value decompositionprincipal component analysisspectral methodshigh-dimensional statisticsProcrustes analysiseigenvector perturbation

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Estimation in multivariate analysis (62H12) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Inference from stochastic processes and spectral analysis (62M15)

Related Items (30)

Estimating Mixed Memberships With Sharp Eigenvector Deviations ⋮ A Schatten-\(q\) low-rank matrix perturbation analysis via perturbation projection error bound ⋮ Asymptotically efficient estimators for stochastic blockmodels: the naive MLE, the rank-constrained MLE, and the spectral estimator ⋮ Singular vector and singular subspace distribution for the matrix denoising model ⋮ Bayesian sparse spiked covariance model with a continuous matrix shrinkage prior ⋮ Compressed spectral screening for large-scale differential correlation analysis with application in selecting glioblastoma gene modules ⋮ Entrywise eigenvector analysis of random matrices with low expected rank ⋮ Euclidean Representation of Low-Rank Matrices and Its Geometric Properties ⋮ Entrywise limit theorems for eigenvectors of signal-plus-noise matrix models with weak signals ⋮ Spectral Clustering via Adaptive Layer Aggregation for Multi-Layer Networks ⋮ Vertex nomination, consistent estimation, and adversarial modification ⋮ Uniform Bounds for Invariant Subspace Perturbations ⋮ Unnamed Item ⋮ The Sup-norm Perturbation of HOSVD and Low Rank Tensor Denoising ⋮ Inference for heteroskedastic PCA with missing data ⋮ On estimation and inference in latent structure random graphs ⋮ Robust high-dimensional factor models with applications to statistical machine learning ⋮ Crowdsourcing Utilizing Subgroup Structure of Latent Factor Modeling ⋮ Subspace estimation from unbalanced and incomplete data matrices: \({\ell_{2,\infty}}\) statistical guarantees ⋮ Unnamed Item ⋮ Strong consistency guarantees for clustering high-dimensional bipartite graphs with the spectral method ⋮ Spectral Embedding of Weighted Graphs ⋮ Leave-one-out singular subspace perturbation analysis for spectral clustering ⋮ Exact minimax optimality of spectral methods in phase synchronization and orthogonal group synchronization ⋮ Applications of dual regularized Laplacian matrix for community detection ⋮ Analysis of spectral clustering algorithms for community detection: the general bipartite setting ⋮ Spectral clustering revisited: information hidden in the Fiedler vector ⋮ A Performance Guarantee for Spectral Clustering ⋮ An \({\ell_p}\) theory of PCA and spectral clustering ⋮ Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A nonparametric two-sample hypothesis testing problem for random graphs
• Spectra of edge-independent random graphs
• Manifold matching: joint optimization of fidelity and commensurability
• Perfect clustering for stochastic blockmodel graphs via adjacency spectral embedding
• Concentration inequalities and moment bounds for sample covariance operators
• The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices
• Spectral clustering and the high-dimensional stochastic blockmodel
• Eigenvectors of random matrices: A survey
• Estimation of functionals of sparse covariance matrices
• Delocalization of eigenvectors of random matrices with independent entries
• Non-Euclidean statistics for covariance matrices, with applications to diffusion tensor imaging
• Finite sample approximation results for principal component analysis: A matrix perturbation approach
• Spectral analysis of large dimensional random matrices
• Norms of random matrices: local and global problems
• New asymptotic results in principal component analysis
• Random perturbation of low rank matrices: improving classical bounds
• Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics
• Limit theorems for eigenvectors of the normalized Laplacian for random graphs
• On the distribution of the largest eigenvalue in principal components analysis
• Principal component analysis.
• Statistics on special manifolds
• Asymptotically efficient estimators for stochastic blockmodels: the naive MLE, the rank-constrained MLE, and the spectral estimator
• Entrywise eigenvector analysis of random matrices with low expected rank
• Consistency of spectral clustering in stochastic block models
• Role of normalization in spectral clustering for stochastic blockmodels
• Sparse PCA: optimal rates and adaptive estimation
• Random matrix theory in statistics: a review
• Exact matrix completion via convex optimization
• Statistical Shape Analysis, with Applications in R
• The Geometry of Algorithms with Orthogonality Constraints
• The Procrustes Problem for Orthogonal Stiefel Matrices
• An $\ell_{\infty}$ Eigenvector Perturbation Bound and Its Application to Robust Covariance Estimation
• High-Dimensional Probability
• A Consistent Adjacency Spectral Embedding for Stochastic Blockmodel Graphs
• Large Sample Covariance Matrices and High-Dimensional Data Analysis
• A useful variant of the Davis–Kahan theorem for statisticians
• Consistent Adjacency-Spectral Partitioning for the Stochastic Block Model When the Model Parameters Are Unknown
• Information Recovery in Shuffled Graphs via Graph Matching
• Random Dot Product Graph Models for Social Networks
• 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
• Large Covariance Estimation by Thresholding Principal Orthogonal Complements
• Estimating Mixed Memberships With Sharp Eigenvector Deviations
• Optimization via low-rank approximation for community detection in networks

This page was built for publication: The two-to-infinity norm and singular subspace geometry with applications to high-dimensional statistics