arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.00717cs.ITmath.IT
收藏

稀疏优化问题的最优$k$ -阈值算法

Optimal $k$-thresholding algorithms for sparse optimization problems

Yun-Bin Zhao

摘要:

仿真结果表明,现有的独立于残差函数的硬阈值技术可能会导致残差的急剧增加或数值振荡。硬阈值的这一固有缺陷使得传统的阈值算法不稳定,从而通常不能有效地解决实际的稀疏优化问题。如何克服这一弱点,开发一种真正有效的阈值方法是该领域的一个基本问题。本文的目的是解决这个问题,提出了一种新的阈值技术的基础上的概念,最佳的$k$阈值。这种新发展的中心思想是在算法过程中将$k$阈值直接连接到残差减少。这导致了有效阈值方法的自然设计原理。在约束等距性(RIP)下,我们证明了基于最优阈值的算法对稀疏优化问题的解是全局收敛的。数值实验表明,在求解稀疏优化问题时,所提算法的性能明显优于传统的硬阈值方法,在很多情况下甚至优于经典的$\ell_1$ -最小化方法.

英文摘要:

The simulations indicate that the existing hard thresholding technique independent of the residual function may cause a dramatic increase or numerical oscillation of the residual. This inherit drawback of the hard thresholding renders the traditional thresholding algorithms unstable and thus generally inefficient for solving practical sparse optimization problems. How to overcome this weakness and develop a truly efficient thresholding method is a fundamental question in this field. The aim of this paper is to address this question by proposing a new thresholding technique based on the notion of optimal $k$-thresholding. The central idea for this new development is to connect the $k$-thresholding directly to the residual reduction during the course of algorithms. This leads to a natural design principle for the efficient thresholding methods. Under the restricted isometry property (RIP), we prove that the optimal thresholding based algorithms are globally convergent to the solution of sparse optimization problems. The numerical experiments demonstrate that when solving sparse optimization problems, the traditional hard thresholding methods have been significantly transcended by the proposed algorithms which can even outperform the classic $\ell_1$-minimization method in many situations.

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。

↑