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 2408.10672cs.LGcs.NE
收藏

神经探索性景观分析用于元黑箱优化

Neural Exploratory Landscape Analysis for Meta-Black-Box-Optimization

South China University of Technology(华南理工大学)

Zeyuan Ma, Jiacheng Chen, Hongshu Guo, Yue-Jiao Gong

AI总结:

本文提出NeurELA,一种端到端、基于注意力两阶段神经网络的框架,用于动态刻画景观特征,替代人工特征,提升元黑箱优化的自主性和性能。

摘要:

近期在元黑箱优化(MetaBBO)领域的研究表明,元训练的神经网络能够有效指导黑箱优化器的设计,显著减少对专家调参的需求,并在复杂问题分布上提供稳健的性能。尽管取得了成功,但仍存在一个悖论:MetaBBO仍然依赖人工设计的探索性景观分析特征来向元级智能体传达低级优化的进展。为解决这一差距,本文提出了神经探索性景观分析(NeurELA),一种新颖的框架,通过两阶段、基于注意力的神经网络动态刻画景观特征,并以完全端到端的方式执行。NeurELA通过多任务神经进化策略在多种MetaBBO算法上进行预训练。大量实验表明,NeurELA在集成到不同甚至未见过的MetaBBO任务中时,始终能取得优越性能,并且可以高效微调以进一步提升性能。这一进展标志着MetaBBO算法向更自主和广泛适用迈出了关键一步。NeurELA的源代码可在https://github.com/GMC-DRL/Neur-ELA获取。

英文摘要:

Recent research in Meta-Black-Box Optimization (MetaBBO) have shown that meta-trained neural networks can effectively guide the design of black-box optimizers, significantly reducing the need for expert tuning and delivering robust performance across complex problem distributions. Despite their success, a paradox remains: MetaBBO still rely on human-crafted Exploratory Landscape Analysis features to inform the meta-level agent about the low-level optimization progress. To address the gap, this paper proposes Neural Exploratory Landscape Analysis (NeurELA), a novel framework that dynamically profiles landscape features through a two-stage, attention-based neural network, executed in an entirely end-to-end fashion. NeurELA is pre-trained over a variety of MetaBBO algorithms using a multi-task neuroevolution strategy. Extensive experiments show that NeurELA achieves consistently superior performance when integrated into different and even unseen MetaBBO tasks and can be efficiently fine-tuned for further performance boost. This advancement marks a pivotal step in making MetaBBO algorithms more autonomous and broadly applicable. The source code of NeurELA can be accessed at https://github.com/GMC-DRL/Neur-ELA.

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。

↑