Singular Vector Perturbation under Gaussian Noise
classification
🧮 math.NA
cs.NAmath.STstat.TH
keywords
singularanalysisdistributiongaussiannoiseundervectorconditions
read the original 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.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.