arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.15876cs.NEmath.OC
收藏

具有学习率自适应的CMA-ES

CMA-ES with Learning Rate Adaptation

Masahiro Nomura, Youhei Akimoto, Isao Ono

AI总结:

本文研究了学习率对CMA-ES性能的影响,提出了一种保持恒定信噪比的学习率自适应机制,有效解决了多峰和噪声问题且无需昂贵的超参数调优。

摘要:

协方差矩阵自适应进化策略(CMA-ES)是解决连续黑盒优化问题最成功的方法之一。CMA-ES的一个实用优势是无需超参数调优即可使用。然而,超参数设置仍对性能有相当大的影响,特别是在求解多峰或噪声问题等困难任务时。本研究全面探讨了学习率对CMA-ES性能的影响,并通过考虑常微分方程证明了采用小学习率的必要性。随后,讨论了理想学习率的设置。基于这些讨论,我们为CMA-ES开发了一种新颖的学习率自适应机制,该机制可保持恒定的信噪比。此外,我们通过数值实验研究了采用所提出的学习率自适应机制的CMA-ES的行为,并将结果与采用固定学习率的CMA-ES以及采用种群大小自适应的CMA-ES获得的结果进行了比较。结果表明,具有所提出的学习率自适应的CMA-ES在无需极其昂贵的学习率调优的情况下,对多峰和/或噪声问题效果良好。

英文摘要:

The covariance matrix adaptation evolution strategy (CMA-ES) is one of the most successful methods for solving continuous black-box optimization problems. A practically useful aspect of the CMA-ES is that it can be used without hyperparameter tuning. However, the hyperparameter settings still have a considerable impact on performance, especially for difficult tasks, such as solving multimodal or noisy problems. This study comprehensively explores the impact of learning rate on the CMA-ES performance and demonstrates the necessity of a small learning rate by considering ordinary differential equations. Thereafter, it discusses the setting of an ideal learning rate. Based on these discussions, we develop a novel learning rate adaptation mechanism for the CMA-ES that maintains a constant signal-to-noise ratio. Additionally, we investigate the behavior of the CMA-ES with the proposed learning rate adaptation mechanism through numerical experiments, and compare the results with those obtained for the CMA-ES with a fixed learning rate and with population size adaptation. The results show that the CMA-ES with the proposed learning rate adaptation works well for multimodal and/or noisy problems without extremely expensive learning rate tuning.

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。

↑