论文标题
用样品存档的广义自我适应粒子群优化算法
Generalized Self-Adapting Particle Swarm Optimization algorithm with archive of samples
论文作者
论文摘要
在本文中，我们增强了广义自我适应粒子群优化算法（GAPSO），该算法最初是在自然2018会议的平行问题解决中引入的，并研究了其特性。关于GAPSO的研究由以下两个假设强调：（1）通过利用所有收集的样品，可以实现优化算法的良好性能，（2）最佳性能可以通过结合使用专门的采样行为（粒度Swarm优化，差异化，差异进化和局部拟合的平方函数）来实现。从软件工程的角度来看，GAPSO将标准粒子群优化算法视为创建通用使用全局优化框架的理想起点。在此框架内，开发了混合优化算法，并测试了各种其他技术（例如算法重新启动管理或适应方案）。该论文介绍了该算法的新版本，缩写为M-GAPSO。与原始GAPSO公式相比，它包括以下四个功能：全局重新启动管理方案，在基于R-Tree的索引中收集的样品（样品的存档/存储器），基于全球粒子性能的采样行为的适应以及对本地搜索的特定方法。上述增强功能导致在可可BBOB测试床和黑盒优化竞争BBCOMP中观察到的M-GAPSO的性能提高了M-GAPSO。同样，对于M-GAPSO的较低维度功能（最高5D）的结果与CMA-ES的最先进版本更好或相当（即在GECCO 2017会议上提出的KL-BIPOP-CMA-ES算法）。
In this paper we enhance Generalized Self-Adapting Particle Swarm Optimization algorithm (GAPSO), initially introduced at the Parallel Problem Solving from Nature 2018 conference, and to investigate its properties. The research on GAPSO is underlined by the two following assumptions: (1) it is possible to achieve good performance of an optimization algorithm through utilization of all of the gathered samples, (2) the best performance can be accomplished by means of a combination of specialized sampling behaviors (Particle Swarm Optimization, Differential Evolution, and locally fitted square functions). From a software engineering point of view, GAPSO considers a standard Particle Swarm Optimization algorithm as an ideal starting point for creating a generalpurpose global optimization framework. Within this framework hybrid optimization algorithms are developed, and various additional techniques (like algorithm restart management or adaptation schemes) are tested. The paper introduces a new version of the algorithm, abbreviated as M-GAPSO. In comparison with the original GAPSO formulation it includes the following four features: a global restart management scheme, samples gathering within an R-Tree based index (archive/memory of samples), adaptation of a sampling behavior based on a global particle performance, and a specific approach to local search. The above-mentioned enhancements resulted in improved performance of M-GAPSO over GAPSO, observed on both COCO BBOB testbed and in the black-box optimization competition BBComp. Also, for lower dimensionality functions (up to 5D) results of M-GAPSO are better or comparable to the state-of-the art version of CMA-ES (namely the KL-BIPOP-CMA-ES algorithm presented at the GECCO 2017 conference).
