Approximation Bounds for Sparse Principal Component Analysis
arXiv:1205.0121
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.
arXiv commentSection 4 substantially clarified. Added comparison with BBP transition for \lambdamax(.)