English

Finite Sample Guarantees for PCA in Non-Isotropic and Data-Dependent Noise

Machine Learning 2017-09-20 v1 Information Theory math.IT

Abstract

This work obtains novel finite sample guarantees for Principal Component Analysis (PCA). These hold even when the corrupting noise is non-isotropic, and a part (or all of it) is data-dependent. Because of the latter, in general, the noise and the true data are correlated. The results in this work are a significant improvement over those given in our earlier work where this "correlated-PCA" problem was first studied. In fact, in certain regimes, our results imply that the sample complexity required to achieve subspace recovery error that is a constant fraction of the noise level is near-optimal. Useful corollaries of our result include guarantees for PCA in sparse data-dependent noise and for PCA with missing data. An important application of the former is in proving correctness of the subspace update step of a popular online algorithm for dynamic robust PCA.

Keywords

Cite

@article{arxiv.1709.06255,
  title  = {Finite Sample Guarantees for PCA in Non-Isotropic and Data-Dependent Noise},
  author = {Namrata Vaswani and Praneeth Narayanamurthy},
  journal= {arXiv preprint arXiv:1709.06255},
  year   = {2017}
}
R2 v1 2026-06-22T21:47:45.876Z