Approximation Bounds for Sparse Principal Component Analysis

Speaker: 
Alexandre d'Aspremont, CMAP-Ecole Polytechnique
Date: 
Feb 8 2013 - 4:30pm
Event type: 
PACM Colloquium
Room: 
Fine 214
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.