Correlated-PCA: Principal Components' Analysis when Data and Noise are Correlated
Abstract
Given a matrix of observed data, Principal Components Analysis (PCA) computes a small number of orthogonal directions that contain most of its variability. Provably accurate solutions for PCA have been in use for a long time. However, to the best of our knowledge, all existing theoretical guarantees for it assume that the data and the corrupting noise are mutually independent, or at least uncorrelated. This is valid in practice often, but not always. In this paper, we study the PCA problem in the setting where the data and noise can be correlated. Such noise is often also referred to as "data-dependent noise". We obtain a correctness result for the standard eigenvalue decomposition (EVD) based solution to PCA under simple assumptions on the data-noise correlation. We also develop and analyze a generalization of EVD, cluster-EVD, that improves upon EVD in certain regimes.
Cite
@article{arxiv.1608.04320,
title = {Correlated-PCA: Principal Components' Analysis when Data and Noise are Correlated},
author = {Namrata Vaswani and Han Guo},
journal= {arXiv preprint arXiv:1608.04320},
year = {2016}
}
Comments
NIPS 2016 (to appear). Longer version submitted to IEEE Trans. Sig. Proc. is at http://www.ece.iastate.edu/~namrata/TSP_corPCA.pdf