无记忆方法的收敛性分析

The analysisfor convergence of memoryless method

分析了无记忆方法的收敛性 ,证明了在 Armijo- Goldstein准则下 ,无记忆优化方法对一般目标函数为全局收敛 ,且对一致凸函数 ,其定步长算法亦是收敛的。

The convergence ofmemorylessmethod forsolving unconstrained optimization problemsisanalysised. It is proved that this new method is globally convergent when applied to a general objective function under inexact line searches( Armijo- Goldstein rule) .Moreover,the fixed step algorithm is convergent for uniformly convex objective functions.