Entrywise Estimation of Singular Vectors of Low-Rank Matrices with Heteroskedasticity and Dependence

Abstract

We propose an estimator for the singular vectors of high-dimensional low-rank matrices corrupted by additive subgaussian noise, where the noise matrix is allowed to have dependence within rows and heteroskedasticity between them. We prove finite-sample ${\ell }_{2,\infty }$ bounds and a Berry-Esseen theorem for the individual entries of the estimator, and we apply these results to high-dimensional mixture models. Our Berry-Esseen theorem clearly shows the geometric relationship between the signal matrix, the covariance structure of the noise, and the distribution of the errors in the singular vector estimation task. These results are illustrated in numerical simulations. Unlike previous results of this type, which rely on assumptions of gaussianity or independence between the entries of the additive noise, handling the dependence between entries in the proofs of these results requires careful leave-one-out analysis and conditioning arguments. Our results depend only on the signal-to-noise ratio, the sample size, and the spectral properties of the signal matrix.

References in corpus (27)

• Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
• Consistency of spectral clustering in stochastic block models
• Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion, and Blind Deconvolution
• Inference and Uncertainty Quantification for Noisy Matrix Completion
• Spectral Methods for Data Science: A Statistical Perspective
• Statistical inference on random dot product graphs: a survey
• Near-optimal bounds for phase synchronization
• Normal approximation and concentration of spectral projectors of sample covariance
• The geometry of kernelized spectral clustering
• Mixed Membership Estimation for Social Networks
• Optimal spectral shrinkage and PCA with heteroscedastic noise
• Unified ${\ell }_{2\to \infty }$ Eigenspace Perturbation Theory for Symmetric Random Matrices
• Two-sample Test of Community Memberships of Weighted Stochastic Block Models
• Bayesian Estimation of Sparse Spiked Covariance Matrices in High Dimensions
• Inference for Heteroskedastic PCA with Missing Data
• Uniform bounds for invariant subspace perturbations
• Universal Rank Inference via Residual Subsampling with Application to Large Networks
• Nonparametric two-sample hypothesis testing for low-rank random graphs of differing sizes
• A Schatten-$q$ Low-rank Matrix Perturbation Analysis via Perturbation Projection Error Bound
• Efficient Estimation for Random Dot Product Graphs via a One-step Procedure
• Minimax Estimation of Linear Functions of Eigenvectors in the Face of Small Eigen-Gaps
• Hypothesis Testing for Equality of Latent Positions in Random Graphs
• Exact Cluster Recovery via Classical Multidimensional Scaling
• Euclidean Representation of Low-Rank Matrices and Its Statistical Applications
• Modified Multidimensional Scaling and High Dimensional Clustering
• A Robust Spectral Clustering Algorithm for Sub-Gaussian Mixture Models with Outliers
• An ${\ell }_p$ theory of PCA and spectral clustering

Cited by in corpus (2)

• Inference for Heteroskedastic PCA with Missing Data
• Matrix Denoising with Partial Noise Statistics: Optimal Singular Value Shrinkage of Spiked F-Matrices