We propose an efficient and provably correct active-set based algorithm for solving the elastic net problem. The proposed algorithm exploits the fact that the nonzero entries of the elastic-net solution fall into an oracle region, which we use to define and efficiently update our active-set estimate. The proposed update rule leads to an iterative algorithm that is shown to converge to the optimal solution in a finite number of iterations. We present experiments for subspace clustering on computer vision datasets that demonstrate the superiority of our method in terms of clustering accuracy and scalability.

Scheduled as part of