Basin of Attraction as a measure of robustness of an optimization algorithm

doi:10.1109/FSKD.2018.8686850

科研成果详情

题名	Basin of Attraction as a measure of robustness of an optimization algorithm
作者	Tsang，Ken K.T.
发表日期	2018-07-02
会议录名称	ICNC-FSKD 2018 - 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery
页码	133-137
摘要	The concept of Basin of Attraction (BOA)from the theory of dynamical systems can be applied to evaluate the robustness of a deterministic optimization algorithm. For an objective function with many local minima, a large BOA with smooth boundaries associated with the global minimum is an important indicator for the robustness of the optimization algorithm. In this paper, numerical examples of BOA for canned commercial optimizer: fmincon in MATLAB's toolbox (Sequential Quadratic Programming, sqp, and Interior-Point Algorithm)are given as illustrations of how BOA can be used as a tool to compare the robustness of optimization algorithms. We also showed in an example of machine learning application, spurious local minima often appear with more training data are added, and these spurious local minima have nothing to do with the legitimate solution. Finally, three different types of quantitative measure of the robustness of an optimization algorithm based on the basin boundaries are proposed.
关键词	Attractor Basin entropy Basin of attraction Dynamical system Fractal boundary Local and global minimum Optimization algorithm Training data Uncertainty exponent
DOI	10.1109/FSKD.2018.8686850
URL	查看来源
语种	英语English
Scopus入藏号	2-s2.0-85064896766
引用统计	被引频次[WOS]：0 [WOS记录] [WOS相关记录]
文献类型	会议论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/6304
专题	北师香港浸会大学
通讯作者	Tsang，Ken K.T.
作者单位	Division of Science Technology,Statistics Program,BNU-HKBU United International College,Zhuhai,China
第一作者单位	北师香港浸会大学
通讯作者单位	北师香港浸会大学
推荐引用方式 GB/T 7714	Tsang，Ken K.T. Basin of Attraction as a measure of robustness of an optimization algorithm[C], 2018: 133-137.