MWWP线搜索下的新共轭梯度法  

A New Conjugate Gradient Method With MWWP Line Search

作　　者：曹尹平 周光辉[1] CAO Yinping;ZHOU Guanghui(School of Mathematical Sciences,Huaibei Normal University,Huaibei 235000,China)

机构地区：[1]淮北师范大学数学科学学院,安徽淮北235000

出　　处：《安庆师范大学学报（自然科学版）》2021年第2期32-36,78,共6页Journal of Anqing Normal University(Natural Science Edition)

基　　金：安徽省高校自然科学研究项目(KJ2020ZD008)。

摘　　要：随着计算机技术的革新和生产生活中大规模无约束优化问题的涌出,为寻求高效快速的方法,本文构造新共轭梯度算法。将一种修正弱Wolfe-Powell线搜索称为MWWP线搜索,使其与具有良好的充分下降性的DPRP共轭梯度法相结合,证明了该算法在新型线搜索下的全局收敛性,并将该算法与传统共轭梯度法进行了数值实验对比,数值实验结果表明了新方法是有效可行的。With the innovation of computer technology and the emergence of large-scale unconstrained optimization problems in production and life,a new conjugate gradient algorithm is constructed in this paper in order to seek an efficient and fast method.A modified weak Wolfe-Powell line search is called MWWP line search,which is combined with the DPPR conjugate gradient method with sufficient descent.The global convergence of the proposed algorithm under the new line search method is proved,and the comparison between the proposed algorithm and the traditional conjugate gradient method is made by numerical experiments.The numerical experiments show that the new method is effective and feasible.

关 键 词：无约束优化 线搜索 共轭梯度法 

分 类 号：O224[理学—运筹学与控制论]