Convex Relaxations for Subset Selection

We use convex relaxation techniques to produce lower bounds on the optimal value of subset selection problems and generate good approximate solutions. We then explicitly bound the quality of these relaxations by studying the approximation ratio of sparse eigenvalue relaxations. Our results are used to improve the performance of branch-and-bound algorithms to produce exact solutions to subset selection problems.

• Type: Journal
• Year: 2010
• Where: CORR
• Authors: Francis Bach, Selin Damla Ahipasaoglu, Alexandre d'Aspremont
• Keywords: Convex Relaxation Techniques, CORR 2010, Education, Selection Problems, Sparse Eigenvalue Relaxations