Perturbation bounds for eigenspaces under a relative gap condition

DOI10.1090/proc/14714zbMath1491.47011arXiv1803.03868OpenAlexW2963684212MaRDI QIDQ5210923

Moritz Jirak, Martin Wahl

Publication date: 16 January 2020

Published in: Proceedings of the American Mathematical Society (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1803.03868

zbMATH Keywords

eigenspacecovariance operatorrelative perturbation boundssubspace distancerelative gap condition

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Perturbation theory of linear operators (47A55)

Related Items (4)

Lower bounds for invariant statistical models with applications to principal component analysis ⋮ Van Trees inequality, group equivariance, and estimation of principal subspaces ⋮ High-probability bounds for the reconstruction error of PCA ⋮ Relative perturbation bounds with applications to empirical covariance operators

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimal eigen expansions and uniform bounds
• Inference for functional data with applications
• Concentration inequalities and moment bounds for sample covariance operators
• Asymptotics and concentration bounds for bilinear forms of spectral projectors of sample covariance
• Asymptotic theory for the principal component analysis of a vector random function: Some applications to statistical inference
• A note on the Hanson-Wright inequality for random vectors with dependencies
• An overview of relative \(\sin\Theta\) theorems for invariant subspaces of complex matrices
• Random perturbation of low rank matrices: improving classical bounds
• Perturbation theory for linear operators.
• Nonasymptotic upper bounds for the reconstruction error of PCA
• Structured random matrices
• Sparse PCA: optimal rates and adaptive estimation
• High-dimensional principal projections
• Concentration Inequalities
• Characterization of LIL behavior in Banach space
• Theory for high-order bounds in functional principal components analysis
• Some estimates of norms of random matrices
• Theoretical Foundations of Functional Data Analysis, with an Introduction to Linear Operators
• A useful variant of the Davis–Kahan theorem for statisticians
• Singular vectors under random perturbation
• The Rotation of Eigenvectors by a Perturbation. III
• Asymptotic Theory for Principal Component Analysis

This page was built for publication: Perturbation bounds for eigenspaces under a relative gap condition