Approximation Bounds for Sparse Principal Component Analysis
Optimization and Control
2012-06-19 v2
Abstract
We produce approximation bounds on a semidefinite programming relaxation for sparse principal component analysis. These bounds control approximation ratios for tractable statistics in hypothesis testing problems where data points are sampled from Gaussian models with a single sparse leading component.
Cite
@article{arxiv.1205.0121,
title = {Approximation Bounds for Sparse Principal Component Analysis},
author = {Alexandre d'Aspremont and Francis Bach and Laurent El Ghaoui},
journal= {arXiv preprint arXiv:1205.0121},
year = {2012}
}
Comments
Section 4 substantially clarified. Added comparison with BBP transition for \lambdamax(.)