Approximation Bounds for Sparse Principal Component Analysis

Friday, February 8, 2013 -
4:30pm to 5:30pm
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.
Speaker: 
Alexandre d'Aspremont
CMAP-Ecole Polytechnique
Event Location: 
Fine Hall 214