PulseAugur
实时 11:48:19

New algorithm AdaE-SAEA optimizes expensive multi-objective problems

研究人员开发了 AdaE-SAEA,这是一种新颖的自适应集成代理辅助进化算法,专为昂贵的 MOP 问题设计。该新方法将代理辅助进化算法集成到元黑盒优化框架中,从而对信息填充标准和基于集成的代理建模进行统一控制。AdaE-SAEA 通过采用装袋和提升技术,专门解决代理建模中的鲁棒性-准确性权衡问题,旨在在优化早期阶段改善探索,在后期阶段改善利用。实验表明,AdaE-SAEA 在现有最先进方法和元黑盒优化方法方面表现更优,其中 TabPFN 被确定为集成学习的有效基础代理模型。 AI

影响 引入了一种优化复杂系统的新方法,有望提高科学和工程应用的效率。

排序理由 该集群包含一篇详细介绍新算法及其实验验证的研究论文。

在 arXiv cs.NE (Neural & Evolutionary) 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Xiao Jin, Yongxiong Wang, Haobo Liu, Yudong Du, Yukun Du ·

    Meta-Black-Box Optimization with Ensemble Surrogate Modeling for Robustness-Accuracy Trade-off within SAEA

    arXiv:2606.00862v1 Announce Type: cross Abstract: Surrogate-assisted evolutionary algorithms (SAEAs) have been widely used for expensive black-box optimization problems. However, their reliance on rigid and manually designed components limits their flexibility and generalization …

  2. arXiv cs.NE (Neural & Evolutionary) TIER_1 English(EN) · Yukun Du ·

    用于SAEA内鲁棒性-准确性权衡的集成代理建模的Meta黑盒优化

    Surrogate-assisted evolutionary algorithms (SAEAs) have been widely used for expensive black-box optimization problems. However, their reliance on rigid and manually designed components limits their flexibility and generalization across tasks. Meta-black-box optimization (MetaBBO…