arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.01062math.OC
收藏

非凸光滑Optimization算法的区域复杂性分析

Regional Complexity Analysis of Algorithms for Nonconvex Smooth Optimization

Frank E. Curtis, Daniel P. Robinson

摘要:

提出了一种刻画非凸光滑最优化问题算法最坏情况性能的策略。当代分析的特点是最坏情况下的性能,提供了一定的假设下,一个目标函数,上界的迭代次数(或功能或衍生评估),直到一个p阶平稳条件近似满足。这可以说导致了基于异常目标而不是实践中通常遇到的目标的保守描述。相比之下,本文提出的策略的特征最坏情况下的性能分别在区域组成的搜索空间。这些区域一般基于导数值的性质来定义。通过这种方式,可以独立于任何特定类别的目标来分析算法的最坏情况性能。然后,一旦给定了一类目标,人们可以获得一个信息丰富的,微调的复杂性分析,仅仅通过划定的类型的区域,包括搜索空间的功能在类。由一阶和二阶导数定义的区域进行了详细讨论,并提供了一些基本的一阶和二阶算法,以尽量减少凸和非凸目标的兴趣时,例如复杂性分析。它还解释了如何将该策略推广到由高阶导数定义的区域,并用于分析高阶算法的行为。

英文摘要:

A strategy is proposed for characterizing the worst-case performance of algorithms for solving nonconvex smooth optimization problems. Contemporary analyses characterize worst-case performance by providing, under certain assumptions on an objective function, an upper bound on the number of iterations (or function or derivative evaluations) required until a pth-order stationarity condition is approximately satisfied. This arguably leads to conservative characterizations based on anomalous objectives rather than on ones that are typically encountered in practice. By contrast, the strategy proposed in this paper characterizes worst-case performance separately over regions comprising a search space. These regions are defined generically based on properties of derivative values. In this manner, one can analyze the worst-case performance of an algorithm independently from any particular class of objectives. Then, once given a class of objectives, one can obtain an informative, fine-tuned complexity analysis merely by delineating the types of regions that comprise the search spaces for functions in the class. Regions defined by first- and second-order derivatives are discussed in detail and example complexity analyses are provided for a few fundamental first- and second-order algorithms when employed to minimize convex and nonconvex objectives of interest. It is also explained how the strategy can be generalized to regions defined by higher-order derivatives and for analyzing the behavior of higher-order algorithms.

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。

↑