非线性无约束优化问题的新共轭梯度法  

A New Conjugate Gradient Method for Nonlinear Unconstrained Optimization Problems

作　　者：黄海[1] 

机构地区：[1]广西民族师范学院数学与计算机科学系,广西崇左532200

出　　处：《河南大学学报（自然科学版）》2014年第2期141-145,共5页Journal of Henan University:Natural Science

基　　金：国家自然科学基金项目(10761001);广西教育厅科研项目(201012MS215);广西民族师范学院科研项目(2013RCGG02)

摘　　要：在DY共轭梯度法的基础上,给出一个新的共轭梯度法公式,在精确线搜索下该公式等价于DY公式.建立了基于新参数公式并采用Wolfe线搜索的共轭梯度算法,证明了算法满足下降性和具有全局收敛性,初步的数值实验结果表明该方法是有效的,适合于求解非线性无约束优化问题.Based on the DY conjugate gradient method, a new conjugate gradient formula was presented, the new formula is the same as the DY formula when the line search is exact. Based on the new formula, a new conjugate gradient algorithm with the Wolfe line search was proposed, the descent property and the global convergence of the algorithm were proved. Preliminary numerical results show that the new method was effective, suitable for solving nonlinear unconstrained optimization problems.

关 键 词：无约束优化 共轭梯度法 全局收敛 数值实验 

分 类 号：O221.2[理学—运筹学与控制论]