Iterative hard thresholding methods for \(l_0\) regularized convex cone programming (Q463721): Difference between revisions

The author presents an iterative hard thresholding (IHT) method and its variant for solving a special \(l_0\) regularized box constrained convex programming. The iteration complexity of the IHT method for finding an \(\epsilon\)-local-optimal solution of the problem is obtained. Furthermore, the author develops a method for solving \(l_0\) regularized convex cone programming by applying the IHT method to its quadratic penalty relation and establishes its iteration complexity for finding an \(\epsilon\)-approximate local minimizer of the problem.