Approximation Bounds for Sparse Principal Component Analysis

Approximation Bounds for Sparse Principal Component Analysis

-
Alexandre d'Aspremont, CMAP-Ecole Polytechnique
Fine Hall 214

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.