Artificial Intelligence ( IF 14.4 ) Pub Date : 2023-12-21 , DOI: 10.1016/j.artint.2023.104061 Mario Alejandro Hevia Fajardo , Dirk Sudholt
In the discrete domain, self-adjusting parameters of evolutionary algorithms (EAs) have emerged as a fruitful research area with many runtime analyses showing that self-adjusting parameters can outperform the best fixed parameters. Most existing runtime analyses focus on elitist EAs on simple problems, for which moderate performance gains were shown. Here we consider a much more challenging scenario: the multimodal function Cliff, defined as an example where a EA is effective, and for which the best known upper runtime bound for standard EAs is .
We prove that a EA self-adjusting the offspring population size λ using success-based rules optimises Cliff in expected generations and expected evaluations. Along the way, we prove tight upper and lower bounds on the runtime for fixed λ (up to a logarithmic factor) and identify the runtime for the best fixed λ as for (up to sub-polynomial factors). Hence, the self-adjusting EA outperforms the best fixed parameter by a factor of at least .
中文翻译:
自我调整的后代种群规模优于悬崖函数的固定参数
在离散领域,进化算法(EA)的自调整参数已成为一个富有成果的研究领域,许多运行时分析表明自调整参数可以优于最佳固定参数。大多数现有的运行时分析都集中在精英 EA 上解决简单问题,这些问题显示出适度的性能提升。在这里,我们考虑一个更具挑战性的场景:多模态函数 Cliff,定义为一个示例,其中EA 是有效的,标准 EA 最著名的运行时上限是。
我们证明一个EA使用基于成功的规则自我调整后代种群大小λ ,从而优化 Cliff预期世代和预期评价。在此过程中,我们证明了固定λ (最多为对数因子)的运行时间的严格上限和下限,并将最佳固定λ的运行时间确定为为了(最多为次多项式因子)。因此,自我调节EA 的性能至少优于最佳固定参数。