摘要
提供了非光滑单值优化的非单调线搜索方法 .基于线性规划的对偶定理 ,目标函数的方向导数可以表示成线性规划问题 ,这在实际计算非单调线搜索子问题时是非常重要的 .在合理的条件下 ,证明了算法的整体收敛性和局部超线性收敛速率 .
We present a nonmonotone line search algorithm for nonsmooth unary optimization problems. Based on the duality theorem of linear programming, the directional derivatives of the objective function can be expressed as a linear programming which is very important in the practical calculation for nonmonotone line search subproblems. A theoretical analysis proves that the proposed algorithm is globally convergent and has a local superlinear rate under some mild conditions.
出处
《上海师范大学学报(自然科学版)》
2001年第2期34-40,共7页
Journal of Shanghai Normal University(Natural Sciences)
基金
Postgraduate Foundation of Shanghai Teachers University
关键词
非单调线搜索技术
单值优化
非线性无约束极小化
收敛性
nonmonotone line search technique
unary optimization
nonlinear unconstrained minimization
convergence