arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.02355cs.LGcs.NE
收藏

Symbol:通过符号方程学习生成灵活的黑盒优化器

Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning

South China University of Technology(华南理工大学);Nanyang Technological University(南洋理工大学)

Jiacheng Chen, Zeyuan Ma, Hongshu Guo, Yining Ma, Jie Zhang, Yue-Jiao Gong

AI总结:

本文提出Symbol框架,通过符号方程学习自动生成闭式黑盒优化规则,利用强化学习元学习生成器,生成的优化器超越现有基线并具备出色的零样本泛化能力。

摘要:

近期针对黑盒优化的元学习(MetaBBO)方法利用神经网络来元学习传统黑盒优化器的配置。尽管这些方法取得了成功,但它们不可避免地受到预定义手工优化器局限性的制约。在本文中,我们提出了Symbol框架,一种通过符号方程学习促进黑盒优化器自动发现的新框架。具体而言,我们提出了一种符号方程生成器(SEG),它能够为特定任务和优化步骤动态生成闭式优化规则。在Symbol框架内,我们进一步开发了基于强化学习的三种不同策略,以高效地元学习SEG。大量实验表明,由Symbol生成的优化器不仅超越了最先进的黑盒优化(BBO)和元学习黑盒优化(MetaBBO)基线,而且在不同问题维度、种群规模和优化范围的全新未见任务上展现出卓越的零样本泛化能力。此外,我们对Symbol框架及其生成的优化规则进行了深入分析,突显了其理想的灵活性和可解释性。

英文摘要:

Recent Meta-learning for Black-Box Optimization (MetaBBO) methods harness neural networks to meta-learn configurations of traditional black-box optimizers. Despite their success, they are inevitably restricted by the limitations of predefined hand-crafted optimizers. In this paper, we present \textsc{Symbol}, a novel framework that promotes the automated discovery of black-box optimizers through symbolic equation learning. Specifically, we propose a Symbolic Equation Generator (SEG) that allows closed-form optimization rules to be dynamically generated for specific tasks and optimization steps. Within \textsc{Symbol}, we then develop three distinct strategies based on reinforcement learning, so as to meta-learn the SEG efficiently. Extensive experiments reveal that the optimizers generated by \textsc{Symbol} not only surpass the state-of-the-art BBO and MetaBBO baselines, but also exhibit exceptional zero-shot generalization abilities across entirely unseen tasks with different problem dimensions, population sizes, and optimization horizons. Furthermore, we conduct in-depth analyses of our \textsc{Symbol} framework and the optimization rules that it generates, underscoring its desirable flexibility and interpretability.

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。

↑