Perturbation of Linear Forms of Singular Vectors Under Gaussian Noise

DOI10.1007/978-3-319-40519-3_18zbMath1353.15034arXiv1506.02764OpenAlexW2980451193MaRDI QIDQ2954054

Dong Xia, Vladimir I. Koltchinskii

Publication date: 11 January 2017

Published in: High Dimensional Probability VII (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1506.02764

zbMATH Keywords

perturbationGaussian noiserandom matrixsingular vector

Mathematics Subject Classification ID

Gaussian processes (60G15) Random matrices (probabilistic aspects) (60B20) Eigenvalues, singular values, and eigenvectors (15A18) Random matrices (algebraic aspects) (15B52)

Related Items

Near-optimal performance bounds for orthogonal and permutation group synchronization via spectral methods, Asymmetry helps: eigenvalue and eigenvector analyses of asymmetrically perturbed low-rank matrices, Optimal Permutation Recovery in Permuted Monotone Matrix Model, Entrywise eigenvector analysis of random matrices with low expected rank, Optimal estimation and computational limit of low-rank Gaussian mixtures, Normal approximation and confidence region of singular subspaces, The Sup-norm Perturbation of HOSVD and Low Rank Tensor Denoising, Robust high-dimensional factor models with applications to statistical machine learning, Subspace estimation from unbalanced and incomplete data matrices: \({\ell_{2,\infty}}\) statistical guarantees, Efficient estimation of smooth functionals in Gaussian shift models, Optimality of spectral clustering in the Gaussian mixture model, Estimation of smooth functionals in normal models: bias reduction and asymptotic efficiency, Spectral method and regularized MLE are both optimal for top-\(K\) ranking, Community detection on mixture multilayer networks via regularized tensor decomposition, An \({\ell_p}\) theory of PCA and spectral clustering, Unnamed Item

Cites Work

• Unnamed Item
• Fast community detection by SCORE
• The singular values and vectors of low rank perturbations of large rectangular random matrices
• Asymptotics and concentration bounds for bilinear forms of spectral projectors of sample covariance
• Spectral clustering and the high-dimensional stochastic blockmodel
• Consistency of spectral clustering in stochastic block models
• Random weighted projections, random quadratic forms and random eigenvectors
• Spectral Algorithms
• Relative Perturbation Theory: II. Eigenspace and Singular Subspace Variations
• Singular Vector Perturbation Under Gaussian Noise
• Singular vectors under random perturbation