Perturbation upper bounds for singular subspaces with a kind of heteroskedastic noise and its application in clustering

DOI10.1002/MMA.8256zbMath1527.62040OpenAlexW4220929153MaRDI QIDQ6087610

Z. Zhang, Jin Ru Wang

Publication date: 12 December 2023

Published in: Mathematical Methods in the Applied Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1002/mma.8256

zbMATH Keywords

clusteringperturbation boundheteroscedastic noisemisclassification ratesingular subspace

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Numerical computation of eigenvalues and eigenvectors of matrices (65F15)

Cites Work

• Unnamed Item
• Reconstruction of a low-rank matrix in the presence of Gaussian noise
• Hanson-Wright inequality and sub-Gaussian concentration
• Random perturbation of low rank matrices: improving classical bounds
• Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics
• Exact matrix completion via convex optimization
• An $\ell_{\infty}$ Eigenvector Perturbation Bound and Its Application to Robust Covariance Estimation
• Maximum likelihood localization of multiple sources by alternating projection
• Improved Subspace Estimation for Multivariate Observations of High Dimension: The Deterministic Signals Case
• Singular vectors under random perturbation
• The Rotation of Eigenvectors by a Perturbation. III
• Perturbation bounds in connection with singular value decomposition
• Compressed sensing

This page was built for publication: Perturbation upper bounds for singular subspaces with a kind of heteroskedastic noise and its application in clustering