arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.04528cs.LGcs.AI
收藏

使用大型语言模型进行超参数优化

Using Large Language Models for Hyperparameter Optimization

University of Toronto(多伦多大学);Vector Institute(向量研究所)

Michael R. Zhang, Nishkrit Desai, Juhan Bae, Jonathan Lorraine, Jimmy Ba

AI总结:

本文利用大型语言模型进行超参数优化,通过提示数据集和模型描述迭代提出配置,在受限预算下匹配或超越贝叶斯优化,并将模型代码作为超参数以增强灵活性。

摘要:

本文探讨了基础大型语言模型(LLMs)在超参数优化(HPO)中的应用。超参数对于决定机器学习模型的有效性至关重要,然而在预算有限的场景下,其优化往往依赖手动方法。通过向LLMs提供数据集和模型描述作为提示,我们开发了一种方法,让LLMs提出超参数配置,并根据模型性能进行迭代优化。我们在标准基准上的实证评估表明,在受限的搜索预算内,LLMs在标准基准上能够匹配甚至超越传统的HPO方法(如贝叶斯优化)在不同模型上的表现。此外,我们提出将指定模型的代码视为一个超参数,由LLM输出,这比现有的HPO方法提供了更大的灵活性。

英文摘要:

This paper explores the use of foundational large language models (LLMs) in hyperparameter optimization (HPO). Hyperparameters are critical in determining the effectiveness of machine learning models, yet their optimization often relies on manual approaches in limited-budget settings. By prompting LLMs with dataset and model descriptions, we develop a methodology where LLMs suggest hyperparameter configurations, which are iteratively refined based on model performance. Our empirical evaluations on standard benchmarks reveal that within constrained search budgets, LLMs can match or outperform traditional HPO methods like Bayesian optimization across different models on standard benchmarks. Furthermore, we propose to treat the code specifying our model as a hyperparameter, which the LLM outputs and affords greater flexibility than existing HPO approaches.

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。

↑