无线搜索下仿射尺度算法的收敛性

Globally Convergence of An Affine-Scaling Algorithm Without Line Search

本文我们考虑求解边界约束优化问题的一个仿射尺度算法。该方法的主要特点是在每次迭代过程中不需要任何线搜索,从而避免了多次调用目标函数的计算。在一定条件下,获得了算法的全局收敛性,数值测试证明了方法的有效性。

In this paper, we consider an affine-scaling algorithm for the bound constrained optimization problem. The main characteristic of the proposed algorithm is that no line search is needed at each iteration, and therefore the estimations of function values are avoided. The global convergence is obtained under certain conditions and we report some numerical tests to show the effectiveness of the algorithm.