基于拟牛顿方程一个改进的非线性共轭梯度算法

A Modified Nonlinear Conjugate Gradient Algorithm Using Secant Conditions

基于拟牛顿方程,借鉴文[1]的思想,本文给出一个改进的具有全局收敛非线性共轭梯度算法。该文的算法对文[1]中算法进行了改进,所产生的搜索方向具有充分下降性。在温和的假设下,新算法具有全局收敛性。最后,数值结果检验其有效性。

In this paper,based on the idea of Ref.[1],we propose a modified conjugate gradient method using secant conditions for unconstrained optimization problems.The proposed algorithm improves the method in Ref.[1],which possesses the following properties:the search direction has the sufficient descent property;the global convergence of the given algorithm will be established under suitable assumptions;numerical results are reported to test its efficiency.