arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.07904cs.LGcs.AI
收藏

基于大语言模型的贝叶斯优化自适应获取选择

Adaptive Acquisition Selection for Bayesian Optimization with Large Language Models

Applied Artificial Intelligence Initiative(应用人工智能计划);Deakin University(德肯大学)

Giang Ngo, Dat Phan Trong, Dang Nguyen, Sunil Gupta, Svetha Venkatesh

AI总结:

本文提出LMABO框架,利用预训练大语言模型作为自适应策略,通过结构化状态表示选择最优获取函数,提升贝叶斯优化性能。

摘要:

贝叶斯优化的关键在于获取函数的选择,但没有单一策略是普遍最优的;最佳选择是非平稳且问题依赖的。现有自适应组合方法往往基于过去函数值进行决策,而忽略了剩余预算或替代模型特征等更丰富的信息。为了解决这个问题,我们引入了LMABO,一种新的框架,将预训练的大语言模型(LLM)作为零样本、在线战略家参与BO过程。在每个迭代中,LMABO使用结构化的状态表示来提示LLM从多样化的组合中选择最合适的获取函数。在50个基准问题的评估中,LMABO在静态、自适应组合和其他基于LLM的基线方法上表现出显著的性能提升。我们展示了LLM的行为是一种全面的策略,能够适应实时进展,证明其优势源于其处理和综合完整优化状态的能力,从而生成有效的自适应策略。

英文摘要:

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.

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。

↑