English

A Second-Order Method for Strongly Convex L1-Regularization Problems

Optimization and Control 2015-01-13 v6

Abstract

In this paper a robust second-order method is developed for the solution of strongly convex l1-regularized problems. The main aim is to make the proposed method as inexpensive as possible, while even difficult problems can be efficiently solved. The proposed approach is a primal-dual Newton Conjugate Gradients (pdNCG) method. Convergence properties of pdNCG are studied and worst-case iteration complexity is established. Numerical results are presented on synthetic sparse least-squares problems and real world machine learning problems.

Keywords

Cite

@article{arxiv.1306.5386,
  title  = {A Second-Order Method for Strongly Convex L1-Regularization Problems},
  author = {Kimon Fountoulakis and Jacek Gondzio},
  journal= {arXiv preprint arXiv:1306.5386},
  year   = {2015}
}

Comments

30 pages, 13 figures, 1 table

R2 v1 2026-06-22T00:38:42.784Z