A useful variant of the Davis--Kahan theorem for statisticians
arXiv:1405.0680
Abstract
The Davis--Kahan theorem is used in the analysis of many statistical procedures to bound the distance between subspaces spanned by population eigenvectors and their sample versions. It relies on an eigenvalue separation condition between certain relevant population and sample eigenvalues. We present a variant of this result that depends only on a population eigenvalue separation condition, making it more natural and convenient for direct application in statistical contexts, and improving the bounds in some cases. We also provide an extension to situations where the matrices under study may be asymmetric or even non-square, and where interest is in the distance between subspaces spanned by corresponding singular vectors.
arXiv comment12 pages
References in corpus (6)
- Sparse PCA: Optimal rates and adaptive estimation
- A Tutorial on Spectral Clustering
- Community Detection in Networks using Graph Distance
- Multivariate Analysis of Nonparametric Estimates of Large Correlation Matrices
- Calibrated Elastic Regularization in Matrix Completion
- Estimation of False Discovery Proportion with Unknown Dependence