Solution methodologies for minimizing a sum of pointwise minima of two functions

被引:0
|
作者
Zuo, Xinyi [1 ]
Jiang, Yi [1 ]
机构
[1] Sichuan Normal Univ, Sch Math Sci, Visual Comp & Virtual Real Key Lab, Chengdu 610066, Sichuan, Peoples R China
基金
芬兰科学院; 中国国家自然科学基金;
关键词
Smooth approximation; ADMM algorithm; DC algorithm; GLOBAL CONVERGENCE; SPARSE; DIFFERENCE;
D O I
10.1007/s11590-022-01866-w
中图分类号
C93 [管理学]; O22 [运筹学];
学科分类号
070105 ; 12 ; 1201 ; 1202 ; 120202 ;
摘要
In this paper, an NP-hard problem of minimizing a sum of pointwise minima of two functions is considered. Using a new equivalent formula, we propose a smooth approximation and an ADMM algorithm for solving the problem. In numerical experiments, we survey four methods including the algorithms proposed in this paper and the known methods. The results of numerical experiments indicate that the performance of each of algorithms could highly depend on the problem and simulation settings.
引用
收藏
页码:75 / 87
页数:13
相关论文
共 50 条