无约束优化一个修正的HS三项共轭梯度法

A Modified HS Three-term Conjugate Gradient Method for Unconstrained Optimization

针对无约束优化问题,本文提出了一个修正的HS三项共轭梯度法。基于拟牛顿方程新型割线条件,提出了具有充分下降性质的改进HS三项共轭梯度参数公式。在弱Wolfe-Powell线搜索技术下,获得了算法的全局收敛性。数值实验结果表明该算法是有效的。

In this paper,a modified Hestenes-Stiefel three-term conjugate gradient method is proposed for unconstrained optimization.Based on the new secant condition of quasi-Newton equation,we propose a modified Hestenes-Stiefel threeterm formula,which has the sufficiently descent property without any conditions.The global convergence under weak WolfePowell line search technique is established for general functions.Numerical experiments show that the proposed algorithm is very effective.