Approximation Bounds for Sparse Principal Component Analysis

COUV_CAHIER_EGND_A1by Alexandre D’aspremont, Francis Bach & Laurent El Ghaoui

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.

Download the paper