Second-order orthant-based methods with enriched Hessian information for sparse $\ell_1$-optimization
Abstract
We present a second order algorithm, based on orthantwise directions, for solving optimization problems involving the sparsity enhancing -norm. The main idea of our method consists in modifying the descent orthantwise directions by using second order information both of the regular term and (in weak sense) of the -norm. The weak second order information behind the -term is incorporated via a partial Huber regularization. One of the main features of our algorithm consists in a faster identification of the active set. We also prove that a reduced version of our method is equivalent to a semismooth Newton algorithm applied to the optimality condition, under a specific choice of the algorithm parameters. We present several computational experiments to show the efficiency of our approach compared to other state-of-the-art algorithms.
Cite
@article{arxiv.1407.1096,
title = {Second-order orthant-based methods with enriched Hessian information for sparse $\ell_1$-optimization},
author = {J. C. De los Reyes and E. Loayza and P. Merino},
journal= {arXiv preprint arXiv:1407.1096},
year = {2016}
}