English

Singular Vector Perturbation under Gaussian Noise

Numerical Analysis 2014-12-12 v3 Statistics Theory Statistics Theory

Abstract

We perform a non-asymptotic 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.

Keywords

Cite

@article{arxiv.1208.1811,
  title  = {Singular Vector Perturbation under Gaussian Noise},
  author = {Rongrong Wang},
  journal= {arXiv preprint arXiv:1208.1811},
  year   = {2014}
}
R2 v1 2026-06-21T21:48:11.877Z