用大模型增强超参优化，让时间序列预测更准更透明
A Meta-Knowledge-Augmented LLM Framework for Hyperparameter Optimization in Time-Series Forecasting
- 将数据元特征与历史调优结果构造成结构化知识，注入大模型提示中
- 在多变量时间序列上相比贝叶斯优化提升预测性能，且决策过程可解释
- 适合需要可解释性超参调优的工业级时间序列建模场景
超参数优化（HPO）对深度学习模型性能至关重要，但在时间序列预测中仍面临计算成本高、可解释性差的问题。尽管贝叶斯优化（BO）是主流方法，但通常独立处理每个任务，难以提供决策依据。我们提出 LLM-AutoOpt，一种融合贝叶斯优化与大语言模型（LLM）上下文推理的混合框架。该框架将数据元特征、模型描述、历史优化结果和目标函数等结构化元知识嵌入LLM提示中，利用BO初始化搜索以缓解冷启动问题。此设计实现了上下文感知且稳定的超参数优化，并揭示了优化过程中的推理逻辑。在多变量时间序列预测基准上的实验表明，相较于标准贝叶斯优化和无元知识的LLM基线，该方法在预测性能和优化可解释性方面均有显著提升。
原文摘要 · Abstract (English)
Hyperparameter optimization (HPO) plays a central role in the performance of deep learning models, yet remains computationally expensive and difficult to interpret, particularly for time-series forecasting. While Bayesian Optimization (BO) is a standard approach, it typically treats tuning tasks independently and provides limited insight into its decisions. Recent advances in large language models (LLMs) offer new opportunities to incorporate structured prior knowledge and reasoning into optimization pipelines. We introduce LLM-AutoOpt, a hybrid HPO framework that combines BO with LLM-based contextual reasoning. The framework encodes dataset meta-features, model descriptions, historical optimization outcomes, and target objectives as structured meta-knowledge within LLM prompts, using BO to initialize the search and mitigate cold-start effects. This design enables context-aware and stable hyperparameter refinement while exposing the reasoning behind optimization decisions. Experiments on a multivariate time series forecasting benchmark demonstrate that LLM-AutoOpt achieves improved predictive performance and more interpretable optimization behavior compared to BO and LLM baselines without meta-knowledge.
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。