用生成模型直接产出优质解，节省昂贵评估预算。
NeurGO: Learning to Generate Elite Candidates for Meta-Black-Box Expensive Optimization
- 基于注意力机制生成高质量候选解，跳过大量无效评估
- 在CEC 2008与COCO BBOB上相同预算下表现更优，收敛更快
- 适合高成本黑箱优化场景，如工程设计与科学建模
昂贵的黑箱优化在科学与工程中普遍存在，函数评估代价高且预算有限。传统进化算法与元黑箱优化（MetaBBO）通常在候选选择上消耗大部分评估次数，常将宝贵预算浪费于低质量解。尽管代理辅助进化与贝叶斯优化试图通过代理模型减少评估，但受限于数据量，构建准确全局模型仍具挑战，且模型偏差易使搜索陷入局部最优。为此，我们提出NeurGO，一种生成式元黑箱优化框架，可直接从历史种群状态合成优质候选解。具体地，采用基于注意力的编码器捕捉种群级搜索趋势，并以该表征为条件，驱动解码器生成高质量候选解，避免对大规模子代池进行昂贵评估。同时设计质量-多样性损失函数，在优化过程中兼顾解的质量与种群多样性。在CEC 2008与COCO BBOB测试集上的大量实验表明，该方法在相同评估预算下取得更优性能，且收敛速度更快。
原文摘要 · Abstract (English)
Expensive black-box optimization is ubiquitous in science and engineering, where function evaluations are costly and the evaluation budget is limited. Traditional evolutionary algorithms and Meta-BlackBox Optimization (MetaBBO) approaches typically consume most evaluations on candidate selection, often wasting precious budget on inferior solutions. Although surrogate-assisted evolution and Bayesian optimization aim to reduce evaluations through surrogate models, constructing an accurate global model from limited data remains challenging, and model bias can easily trap the search in local optima. To overcome these limitations, we propose NeurGO, a generative MetaBBO framework that directly synthesizes elite candidates from historical population states. Specifically, we employ an attention-based encoder to capture the population-level search trend and condition a decoder on this representation to generate high-quality candidates, avoiding the expensive evaluation of large offspring pools. We then design a quality-diversity loss to maintain solution quality and population diversity throughout the search. Through extensive benchmarking on CEC 2008 and the COCO BBOB test suites, our method achieves better optimization performance under the same evaluation budget and exhibits faster convergence.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。