Features for Exploiting Black-Box Optimization Problem Structure
Features for Exploiting Black-Box Optimization Problem Structure
复制标题
DOI：
10.1007/978-3-642-44973-4_4
复制
发表时间：
2013-01
期刊：
影响因子：
--
通讯作者：
Tinus Abell;Y. Malitsky;Kevin Tierney
中科院分区：
文献类型：
--
作者：
Tinus Abell;Y. Malitsky;Kevin Tierney
黑盒优化问题(BBO)存在于众多的科学和工程应用中，其特点是目标函数计算量大，严重限制了可执行评估的数量。我们提出了一组稳健的特征来分析BBO问题的适应度情况，并展示了算法组合方法如何利用这些通用的、与问题无关的特征并优于任何单一最小化搜索策略的利用。我们使用来自2012年BBO基准的GECCO研讨会的数据来测试我们的方法，该研讨会包含21个最先进的求解器，运行在24个成熟的函数上。
Black-box optimization (BBO) problems arise in numerous scientific and engineering applications and are characterized by computationally intensive objective functions, which severely limit the number of evaluations that can be performed. We present a robust set of features that analyze the fitness landscape of BBO problems and show how an algorithm portfolio approach can exploit these general, problem independent, features and outperform the utilization of any single minimization search strategy. We test our methodology on data from the GECCO Workshop on BBO Benchmarking 2012, which contains 21 state-of-the-art solvers run on 24 well-established functions.