不等式约束优化一个可行序列线性方程组算法  

A feasible sequential systems of linear equations algorithm for inequality constrained optimization

作　　者：马国栋[1] 简金宝[1] 

机构地区：[1]玉林师范学院,广西高校复杂系统优化与大数据处理重点实验室,广西玉林53700

出　　处：《运筹学学报》2015年第4期48-58,共11页Operations Research Transactions

基　　金：国家自然科学基金(No.11271086);广西自然科学基金(2014GXNSFFA118001);广西高校科研项目(KY2015YB242);广西高校人才小高地创新团队资助项目

摘　　要：提出了求解非线性不等式约束优化问题的一个可行序列线性方程组算法.在每次迭代中,可行下降方向通过求解两个线性方程组产生,系数矩阵具有较好的稀疏性.在较为温和的条件下,算法具有全局收敛性和强收敛性,数值试验表明算法是有效的.In this paper, a feasible sequential system of linear equations algorithm for inequality constrained optimization is proposed. At each iteration, the proposed algorithm solves only two systems of linear equations with a same coefficient matrix to obtain the feasible descent direction. Furthermore, the sparsity of the coefficient matrix is good. Under some necessary assumptions, the algorithm possesses global and strong convergence. Finally, some preliminary numerical experiments are reported to show that the algorithm is effective.

关 键 词：不等式约束优化 线性方程组 算法 全局收敛性 强收敛性 

分 类 号：O221.2[理学—运筹学与控制论]