arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.05274math.OC
收藏

线搜索类型无导数算法的最坏情况复杂度界限

Worst case complexity bounds for linesearch-type derivative-free algorithms

Andrea Brilli, Morteza Kimiaei, Giampaolo Liuzzi, Stefano Lucidi

AI总结:

本文研究了线搜索类型无导数算法的最坏情况复杂度界限,证明了两种算法在非凸光滑函数优化中的O(ε^{-2})复杂度特性。

摘要:

本文致力于分析线搜索类型无导数算法在最小化一般非凸光滑函数时的最坏情况复杂度界限。我们证明了两种线搜索类型算法具有与模式和直接搜索算法相同的复杂度特性。特别地,我们考虑了基于两种不同线搜索技术的两种无导数算法,并证明了在最坏情况下,将目标函数梯度范数驱动到给定阈值ε以下所需的迭代次数和函数评估次数为O(ε^{-2})。

英文摘要:

This paper is devoted to the analysis of worst case complexity bounds for linesearch-type derivative-free algorithms for the minimization of general non-convex smooth functions. We prove that two linesearch-type algorithms enjoy the same complexity properties which have been proved for pattern and direct search algorithms. In particular, we consider two derivative-free algorithms based on two different linesearch techniques and manage to prove that the number of iterations and of function evaluations required to drive the norm of the gradient of the objective function below a given threshold $ε$ is ${\cal O}(ε^{-2})$ in the worst case.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑