arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1407.0286math.NAcs.LGcs.NAstat.ML
收藏

基于DC近似方法的稀疏优化

DC approximation approaches for sparse optimization

Laboratory of Theoretical and Applied Computer Science EA 3097(理论与应用计算机科学实验室);University of Lorraine(洛林大学);Laboratory of Mathematics, INSA - Rouen, University of Normandie(数学实验室,鲁昂INSA,诺曼底大学)

Hoai An Le Thi, Tao Pham Dinh, Hoai Minh Le, Xuan Thanh Vo

AI总结:

本文从DC框架出发,研究了稀疏优化的非凸近似方法,分析了近似问题与原问题的解的一致性,并开发了四种DCA方案,用于解决零范数和稀疏优化问题。

摘要:

稀疏优化是指目标或约束中包含零范数的优化问题。本文从DC(差分凸函数)编程框架出发,研究了稀疏优化的非凸近似方法。考虑了包含所有标准稀疏诱导惩罚函数的零范数的常见DC近似,研究了近似问题与原问题的全局最小值(或局部最小值)的一致性。证明了在某些情况下,近似问题的某些全局最小值(或局部最小值)也是原问题的。利用DC编程中的精确惩罚技术,证明了某些特定近似方法在合适参数下与原问题等价。对几种稀疏诱导惩罚函数的效率进行了全面分析。开发了四种DCA(DC算法)方案,涵盖了非凸稀疏近似方法中的所有标准算法作为特殊版本。这些算法可以视为ℓ₁扰动算法/加权ℓ₁算法。本文提供了一种统一的非凸近似方法,结合了坚实的理论工具和基于DC编程和DCA的高效算法,以解决零范数和稀疏优化问题。作为应用,我们实现了我们的方法用于SVM(支持向量机)问题的特征选择,并在各种近似函数上进行了实证比较数值实验。

英文摘要:

Sparse optimization refers to an optimization problem involving the zero-norm in objective or constraints. In this paper, nonconvex approximation approaches for sparse optimization have been studied with a unifying point of view in DC (Difference of Convex functions) programming framework. Considering a common DC approximation of the zero-norm including all standard sparse inducing penalty functions, we studied the consistency between global minimums (resp. local minimums) of approximate and original problems. We showed that, in several cases, some global minimizers (resp. local minimizers) of the approximate problem are also those of the original problem. Using exact penalty techniques in DC programming, we proved stronger results for some particular approximations, namely, the approximate problem, with suitable parameters, is equivalent to the original problem. The efficiency of several sparse inducing penalty functions have been fully analyzed. Four DCA (DC Algorithm) schemes were developed that cover all standard algorithms in nonconvex sparse approximation approaches as special versions. They can be viewed as, an $\ell _{1}$-perturbed algorithm / reweighted-$\ell _{1}$ algorithm / reweighted-$\ell _{1}$ algorithm. We offer a unifying nonconvex approximation approach, with solid theoretical tools as well as efficient algorithms based on DC programming and DCA, to tackle the zero-norm and sparse optimization. As an application, we implemented our methods for the feature selection in SVM (Support Vector Machine) problem and performed empirical comparative numerical experiments on the proposed algorithms with various approximation functions.

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。

↑