摘要
提出了一个处理无约束非光滑优化问题的信赖域算法 .它仅要求目标函数是下半连续的 ,而不是光滑的 ,或凸的 ,或局部Lipschitzian的 ,从而扩大了信赖域方法的使用范围 .
The classical trust region algorithm for smooth nonlinear programming is extended to the nonsmooth case where the objective function is only lower semicontinuous in R n. At each iteration, the objective function is approximated by the first order approximate function that satisfies some assumptions, and the search direction is obtained by solving an easy problem. It is proven that each accumulation point of the iteration point sequence generated by this algorithm is a critical point of the primitive problem.
关键词
信赖域算法
下半连续性
临界点
无约束
非线性规则
nonsmooth optimization
trust region methods
lower semicontinuity
critical point
