An _ eigenvector perturbation bound and its application
From MaRDI portal
Publication:4558538
Abstract: In statistics and machine learning, people are often interested in the eigenvectors (or singular vectors) of certain matrices (e.g. covariance matrices, data matrices, etc). However, those matrices are usually perturbed by noises or statistical errors, either from random sampling or structural patterns. One usually employs Davis-Kahan theorem to bound the difference between the eigenvectors of a matrix and those of a perturbed matrix , in terms of norm. In this paper, we prove that when is a low-rank and incoherent matrix, the norm perturbation bound of singular vectors (or eigenvectors in the symmetric case) is smaller by a factor of or for left and right vectors, where and are the matrix dimensions. The power of this new perturbation result is shown in robust covariance estimation, particularly when random variables have heavy tails. There, we propose new robust covariance estimators and establish their asymptotic properties using the newly developed perturbation bound. Our theoretical results are verified through extensive numerical experiments.
Recommendations
- Optimality of singular vector perturbation under maximum norm
- Singular vectors under random perturbation
- Unperturbed: spectral analysis beyond Davis-Kahan
- Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics
- Random perturbation of low rank matrices: improving classical bounds
Cites work
- scientific article; zbMATH DE number 45785 (Why is no real title available?)
- scientific article; zbMATH DE number 47363 (Why is no real title available?)
- scientific article; zbMATH DE number 1849957 (Why is no real title available?)
- A distributed method for solving semidefinite programs arising from ad hoc wireless sensor network localization
- A framework for robust subspace learning
- A multivariate version of kendall's τ
- A useful variant of the Davis-Kahan theorem for statisticians
- Arbitrage, Factor Structure, and Mean-Variance Analysis on Large Asset Markets
- Asymptotics of empirical eigenstructure for high dimensional spiked covariance
- Challenging the empirical mean and empirical variance: a deviation study
- Common risk factors in the returns on stocks and bonds
- Covariance regularization by thresholding
- Dimension Reduction and Coefficient Estimation in Multivariate Linear Regression
- Elliptically contoured models in statistics and portfolio theory
- Estimation of High Dimensional Mean Regression in the Absence of Symmetry and Light Tail Assumptions
- Forecasting Using Principal Components From a Large Number of Predictors
- Generalized thresholding of large covariance matrices
- High dimensional covariance matrix estimation using a factor model
- Incoherence-Optimal Matrix Completion
- Inferential Theory for Factor Models of Large Dimensions
- Latent variable models and factor analysis. A unified approach
- Minimax sparse principal subspace estimation in high dimensions
- Modern multidimensional scaling. Theory and applications.
- On consistency and sparsity for principal components analysis in high dimensions
- Optimal detection of sparse principal components in high dimension
- Perturbation bounds in connection with singular value decomposition
- Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
- Principal component analysis.
- Random perturbation of low rank matrices: improving classical bounds
- Rank-Sparsity Incoherence for Matrix Decomposition
- Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics
- Regularization of Wavelet Approximations
- Robust Estimation of a Location Parameter
- Robust principal component analysis?
- SYMMETRIC GAUGE FUNCTIONS AND UNITARILY INVARIANT NORMS
- Scale-invariant sparse PCA on high-dimensional meta-elliptical data
- Singular vectors under random perturbation
- Sparse principal component analysis and iterative thresholding
- Spectral clustering and the high-dimensional stochastic blockmodel
- The Rotation of Eigenvectors by a Perturbation. III
- User-friendly tail bounds for sums of random matrices
Cited in
(45)- The Sup-norm Perturbation of HOSVD and Low Rank Tensor Denoising
- scientific article; zbMATH DE number 7415122 (Why is no real title available?)
- A Spectral Method for Joint Community Detection and Orthogonal Group Synchronization
- Bridging convex and nonconvex optimization in robust PCA: noise, outliers and missing data
- Strong consistency, graph Laplacians, and the stochastic block model
- Subspace estimation from unbalanced and incomplete data matrices: \({\ell_{2,\infty}}\) statistical guarantees
- On the \(\ell^\infty\)-norms of the singular vectors of arbitrary powers of a difference matrix with applications to sigma-delta quantization
- Polynomial-Time Algorithms for Continuous Metrics on Atomic Clouds of Unordered Points
- Euclidean Representation of Low-Rank Matrices and Its Geometric Properties
- scientific article; zbMATH DE number 7370530 (Why is no real title available?)
- Exact minimax optimality of spectral methods in phase synchronization and orthogonal group synchronization
- Leave-one-out singular subspace perturbation analysis for spectral clustering
- Unperturbed: spectral analysis beyond Davis-Kahan
- Robust high-dimensional factor models with applications to statistical machine learning
- A useful variant of the Davis-Kahan theorem for statisticians
- Singular vector and singular subspace distribution for the matrix denoising model
- Signal-plus-noise matrix models: eigenvector deviations and fluctuations
- Inference for heteroskedastic PCA with missing data
- Relative perturbation bounds with applications to empirical covariance operators
- Large volatility matrix analysis using global and national factor models
- Learning low-dimensional nonlinear structures from high-dimensional noisy data: an integral operator approach
- Non-asymptotic properties of spectral decomposition of large Gram-type matrices and applications
- Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics
- Near-optimal performance bounds for orthogonal and permutation group synchronization via spectral methods
- Perturbation upper bounds for singular subspaces with a kind of heteroskedastic noise and its application in clustering
- Optimality of singular vector perturbation under maximum norm
- Entrywise limit theorems for eigenvectors of signal-plus-noise matrix models with weak signals
- Learning Gaussian graphical models with latent confounders
- Solving jigsaw puzzles by the graph connection Laplacian
- Spectral method and regularized MLE are both optimal for top-\(K\) ranking
- Adaptive robust large volatility matrix estimation based on high-frequency financial data
- High-dimensional volatility matrix estimation with cross-sectional dependent and heavy-tailed microstructural noise
- Strong consistency guarantees for clustering high-dimensional bipartite graphs with the spectral method
- A performance guarantee for spectral clustering
- Compressed spectral screening for large-scale differential correlation analysis with application in selecting glioblastoma gene modules
- Robust covariance estimation with noisy high-frequency financial data
- scientific article; zbMATH DE number 7255037 (Why is no real title available?)
- Improved performance guarantees for orthogonal group synchronization via generalized power method
- Testing Simultaneous Diagonalizability
- Uniform Bounds for Invariant Subspace Perturbations
- Asymptotic Theory of Eigenvectors for Random Matrices With Diverging Spikes
- Singular vector distribution of sample covariance matrices
- The two-to-infinity norm and singular subspace geometry with applications to high-dimensional statistics
- Asymmetry helps: eigenvalue and eigenvector analyses of asymmetrically perturbed low-rank matrices
- Entrywise eigenvector analysis of random matrices with low expected rank
This page was built for publication: An \(\ell_{\infty}\) eigenvector perturbation bound and its application
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4558538)
