arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1306.5386math.OC
收藏

强凸L1-Regularization问题的二阶方法

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

Kimon Fountoulakis, Jacek Gondzio

摘要:

本文发展了一种鲁棒二阶方法来求解强凸l1正则化问题。主要目的是使所提出的方法尽可能便宜,而即使是困难的问题也可以有效地解决。所提出的方法是一个原始-对偶牛顿共轭矩阵(pdNCG)方法。研究了pdNCG的收敛性,并建立了最坏情况下的迭代复杂度.在合成稀疏最小二乘问题和现实世界的机器学习问题的数值结果。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑