用大模型动态选最优优化策略，提升贝叶斯优化效率
Adaptive Acquisition Selection for Bayesian Optimization with Large Language Models
- 用预训练大模型实时分析优化状态，自动选择最佳采集函数
- 在50个基准问题上性能显著优于静态和传统自适应方法
- 适合需要高效调参的科研与工程场景
贝叶斯优化依赖采集函数的选择，但无通用最优策略；最佳选择随问题变化。现有自适应组合方法多基于历史函数值，忽略剩余预算和代理模型特征等信息。为此，我们提出LMABO框架，将预训练大语言模型（LLM）作为零样本、在线策略制定者。每轮迭代中，LMABO通过结构化状态表示提示LLM从多样采集函数组合中选出最适者。在50个基准问题上的评估显示，LMABO显著优于强静态、自适应组合及其他基于LLM的基线。结果表明，LLM的行为是一种综合策略，能根据实时进展自适应调整，其优势源于对完整优化状态的综合处理能力。
原文摘要 · Abstract (English)
Bayesian Optimization critically depends on the choice of acquisition function, but no single strategy is universally optimal; the best choice is non-stationary and problem-dependent. Existing adaptive portfolio methods often base their decisions on past function values while ignoring richer information like remaining budget or surrogate model characteristics. To address this, we introduce LMABO, a novel framework that casts a pre-trained Large Language Model (LLM) as a zero-shot, online strategist for the BO process. At each iteration, LMABO uses a structured state representation to prompt the LLM to select the most suitable acquisition function from a diverse portfolio. In an evaluation across 50 benchmark problems, LMABO demonstrates a significant performance improvement over strong static, adaptive portfolio, and other LLM-based baselines. We show that the LLM's behavior is a comprehensive strategy that adapts to real-time progress, proving its advantage stems from its ability to process and synthesize the complete optimization state into an effective, adaptive policy.
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。