约束优化无罚函数非单调SQP算法(英文)

NONMONOTONE SQP METHODS FOR NONLINEAR PROGRAMMING WITHOUT A PENALTY FUNCTION

本文研究求解非线性约束优化问题.利用非单调无罚函数方法,提出了一个新的序列二次规划算法.该算法在每次迭代过程中只需求解一个QP子问题和一个线性方程组.在一般条件下,算法具有全局收敛性.数值结果表明,计算量小于单调且含罚函数的传统算法.

In this paper,we aim to solve nonlinear constrained optimization.By making use of penalty-function-free nonmonotone method,a new sequential quadratic programming（SQP） algorithm is proposed.It only needs to solve one QP subproblem and one linear system at each iteration.Under reasonable conditions,the global convergence is established.Numerical results show that the computational costs are obviously less than the traditional algorithm with monotone and penalty function.