The two-to-infinity norm and singular subspace geometry with applications to high-dimensional statistics
From MaRDI portal
(Redirected from Publication:2328047)
Abstract: The singular value matrix decomposition plays a ubiquitous role throughout statistics and related fields. Myriad applications including clustering, classification, and dimensionality reduction involve studying and exploiting the geometric structure of singular values and singular vectors. This paper provides a novel collection of technical and theoretical tools for studying the geometry of singular subspaces using the two-to-infinity norm. Motivated by preliminary deterministic Procrustes analysis, we consider a general matrix perturbation setting in which we derive a new Procrustean matrix decomposition. Together with flexible machinery developed for the two-to-infinity norm, this allows us to conduct a refined analysis of the induced perturbation geometry with respect to the underlying singular vectors even in the presence of singular value multiplicity. Our analysis yields singular vector entrywise perturbation bounds for a range of popular matrix noise models, each of which has a meaningful associated statistical inference task. In addition, we demonstrate how the two-to-infinity norm is the preferred norm in certain statistical settings. Specific applications discussed in this paper include covariance estimation, singular subspace recovery, and multiple graph inference. Both our Procrustean matrix decomposition and the technical machinery developed for the two-to-infinity norm may be of independent interest.
Recommendations
- Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics
- High-dimensional \(p\)-norms
- Estimation in high dimensions: a geometric perspective
- scientific article; zbMATH DE number 1740315
- scientific article; zbMATH DE number 1302143
- Asymptotic normality of interpoint distances for high-dimensional data with applications to the two-sample problem
- A high-dimensional two-sample test for the mean using random subspaces
- An introduction to recent advances in high/infinite dimensional statistics
- The geometry of statistical efficiency and matrix statistics
- Perspective functions: proximal calculus and applications in high-dimensional statistics
Cites work
- scientific article; zbMATH DE number 47363 (Why is no real title available?)
- scientific article; zbMATH DE number 967931 (Why is no real title available?)
- A Consistent Adjacency Spectral Embedding for Stochastic Blockmodel Graphs
- A nonparametric two-sample hypothesis testing problem for random graphs
- A useful variant of the Davis-Kahan theorem for statisticians
- An \(\ell_{\infty}\) eigenvector perturbation bound and its application
- Asymptotically efficient estimators for stochastic blockmodels: the naive MLE, the rank-constrained MLE, and the spectral estimator
- Concentration inequalities and moment bounds for sample covariance operators
- Consistency of spectral clustering in stochastic block models
- Consistent adjacency-spectral partitioning for the stochastic block model when the model parameters are unknown
- Delocalization of eigenvectors of random matrices with independent entries
- Eigenvectors of random matrices: A survey
- Entrywise eigenvector analysis of random matrices with low expected rank
- Estimating Mixed Memberships With Sharp Eigenvector Deviations
- Estimation of functionals of sparse covariance matrices
- Exact matrix completion via convex optimization
- Finite sample approximation results for principal component analysis: A matrix perturbation approach
- High-dimensional probability. An introduction with applications in data science
- Information Recovery in Shuffled Graphs via Graph Matching
- Large covariance estimation by thresholding principal orthogonal complements. With discussion and authors' reply
- Large sample covariance matrices and high-dimensional data analysis
- Limit theorems for eigenvectors of the normalized Laplacian for random graphs
- Manifold matching: joint optimization of fidelity and commensurability
- New asymptotic results in principal component analysis
- Non-Euclidean statistics for covariance matrices, with applications to diffusion tensor imaging
- Norms of random matrices: local and global problems
- On the distribution of the largest eigenvalue in principal components analysis
- Optimization via low-rank approximation for community detection in networks
- Perfect clustering for stochastic blockmodel graphs via adjacency spectral embedding
- Perturbation bounds in connection with singular value decomposition
- Principal component analysis.
- Random Dot Product Graph Models for Social Networks
- Random matrix theory in statistics: a review
- Random perturbation of low rank matrices: improving classical bounds
- Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics
- Role of normalization in spectral clustering for stochastic blockmodels
- Signal-plus-noise matrix models: eigenvector deviations and fluctuations
- Sparse PCA: optimal rates and adaptive estimation
- Spectra of edge-independent random graphs
- Spectral analysis of large dimensional random matrices
- Spectral clustering and the high-dimensional stochastic blockmodel
- Statistical shape analysis. With applications in R
- Statistics on special manifolds
- The Geometry of Algorithms with Orthogonality Constraints
- The Procrustes Problem for Orthogonal Stiefel Matrices
- The Rotation of Eigenvectors by a Perturbation. III
- The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices
- Unperturbed: spectral analysis beyond Davis-Kahan
Cited in
(32)- A Schatten-q low-rank matrix perturbation analysis via perturbation projection error bound
- Compressed spectral screening for large-scale differential correlation analysis with application in selecting glioblastoma gene modules
- Crowdsourcing Utilizing Subgroup Structure of Latent Factor Modeling
- A note on the orthogonal Procrustes problem and norm-dependent optimality
- Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics
- The Sup-norm Perturbation of HOSVD and Low Rank Tensor Denoising
- Entrywise eigenvector analysis of random matrices with low expected rank
- Normal approximation and confidence region of singular subspaces
- Asymptotically efficient estimators for stochastic blockmodels: the naive MLE, the rank-constrained MLE, and the spectral estimator
- Strong consistency guarantees for clustering high-dimensional bipartite graphs with the spectral method
- Uniform Bounds for Invariant Subspace Perturbations
- Entrywise limit theorems for eigenvectors of signal-plus-noise matrix models with weak signals
- A performance guarantee for spectral clustering
- Robust high-dimensional factor models with applications to statistical machine learning
- Spectral Clustering via Adaptive Layer Aggregation for Multi-Layer Networks
- Subspace estimation from unbalanced and incomplete data matrices: \({\ell_{2,\infty}}\) statistical guarantees
- On estimation and inference in latent structure random graphs
- scientific article; zbMATH DE number 7415122 (Why is no real title available?)
- Spectral Embedding of Weighted Graphs
- Estimating Mixed Memberships With Sharp Eigenvector Deviations
- scientific article; zbMATH DE number 7625156 (Why is no real title available?)
- Euclidean Representation of Low-Rank Matrices and Its Geometric Properties
- Exact minimax optimality of spectral methods in phase synchronization and orthogonal group synchronization
- Leave-one-out singular subspace perturbation analysis for spectral clustering
- Spectral clustering revisited: information hidden in the Fiedler vector
- Applications of dual regularized Laplacian matrix for community detection
- Vertex nomination, consistent estimation, and adversarial modification
- Singular vector and singular subspace distribution for the matrix denoising model
- Bayesian sparse spiked covariance model with a continuous matrix shrinkage prior
- An \({\ell_p}\) theory of PCA and spectral clustering
- Analysis of spectral clustering algorithms for community detection: the general bipartite setting
- Inference for heteroskedastic PCA with missing data
This page was built for publication: The two-to-infinity norm and singular subspace geometry with applications to high-dimensional statistics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2328047)
