Ask a Question

Prefer a chat interface with context about you and your work?

Singular Vector Perturbation Under Gaussian Noise

Singular Vector Perturbation Under Gaussian Noise

We perform a nonasymptotic analysis on the singular vector distribution under Gaussian noise. In particular, we provide sufficient conditions on a matrix for its first few singular vectors to have near normal distribution. Our result can be used to facilitate the error analysis in linear dimension reduction.