一种约束非光滑优化问题的信赖域算法

A Trust Region Algorithm for Constrained Nonsmooth Optimization

提出了一种易实施的求解带线性约束的非光滑优化问题的信赖域算法 ,并在一定的条件下证明了该算法所产生的迭代序列的任何聚点都是原问题的稳定点 .有限的数值例子表明 。

In this paper, a trust region algorithm TR for linearly constrained optimization is given. Under some conditions, we prove that each accumulation point of the algorithm TR is a stationary point of the primitive problem. The limited numerical experiment show the efficiency of the given method.