一种具有充分下降性的修正DL型谱共轭梯度法  

A modified DL-type spectral conjugate gradient method with sufficiently descent property

作　　者：李亚敏 LI Yamin(School of Economics,Technology&Media University of Henan Kaifeng,Kaifeng 47500l,China)

机构地区：[1]河南开封科技传媒学院经济学院,河南开封475001

出　　处：《浙江理工大学学报（自然科学版）》2023年第2期279-284,共6页Journal of Zhejiang Sci-Tech University(Natural Sciences)

摘　　要：提出了一种大规模无约束优化问题的求解方法,通过修正Dai-Liao(DL)共轭梯度法的共轭参数和谱共轭梯度法的谱参数,构造了一种修正DL型谱共轭梯度法。所选取的谱参数使得每次迭代都自动产生一个不依赖于任何线搜索的下降方向;在常规假设下,利用强Wolfe线搜索证明了此方法对一致凸函数是全局收敛的。A method for solving large-scale unconstrained optimization problems is proposed. By modifying the conjugate parameter of the Dai-Liao(DL) conjugate gradient method and the spectral parameter of the spectral conjugate gradient method, a modified DL-type spectral conjugate gradient method is constructed. The spectral parameter is selected so that each iteration automatically generates a descent direction that does not depend on any line search. Under conventional assumptions, it is proved that this method is globally convergent for uniformly convex functions by using strong Wolfe line search.

关 键 词：无约束优化 强Wolfe线搜索 谱共轭梯度法 谱参数 全局收敛 

分 类 号：O221.2[理学—运筹学与控制论]