面向混合整数线性规划的基础模型研究
Towards Foundation Models for Mixed Integer Linear Programming
AI总结:
针对现有MILP深度学习方法泛化性差、数据集不足的问题,提出基于LLM的进化框架MILP-Evolve生成多样化数据,训练MILP基础模型,在三类任务及MIPLIB基准上取得显著提升,推动MILP基础模型研究。
摘要:
混合整数线性规划(Mixed Integer Linear Programming, MILP)是复杂决策问题建模的核心工具,但存在计算可处理性难题,且需要专家完成问题建模。当前面向MILP的深度学习方法仅针对特定问题类别,无法泛化到未见过的类别。为弥补这一缺陷,我们采用基础模型训练思路,在多样化的MILP问题集合上训练单个深度学习模型,以实现跨问题类别的泛化。由于现有MILP数据集缺乏多样性且数据量不足,我们提出MILP-Evolve——一种基于大语言模型(LLM)的新型进化框架,能够生成大量多样化的MILP类别,并提供无限数量的实例。我们围绕三类覆盖MILP不同维度的核心学习任务验证方法:(1)整数间隙预测;(2)学习分支;(3)MILP实例与自然语言描述对齐这一新任务。实验结果表明,使用MILP-Evolve生成数据训练的模型在未见过的问题(包括MIPLIB基准)上取得显著提升。本研究展现了MILP领域向基础模型方向发展的潜力,这类模型可泛化至广泛的MILP应用场景。我们的代码和数据已在https://github.com/microsoft/OptiGuide公开。
英文摘要:
Mixed Integer Linear Programming (MILP) is essential for modeling complex decision-making problems but faces challenges in computational tractability and requires expert formulation. Current deep learning approaches for MILP focus on specific problem classes and do not generalize to unseen classes. To address this shortcoming, we take a foundation model training approach, where we train a single deep learning model on a diverse set of MILP problems to generalize across problem classes. As existing datasets for MILP lack diversity and volume, we introduce MILP-Evolve, a novel LLM-based evolutionary framework that is capable of generating a large set of diverse MILP classes with an unlimited amount of instances. We study our methodology on three key learning tasks that capture diverse aspects of MILP: (1) integrality gap prediction, (2) learning to branch, and (3) a new task of aligning MILP instances with natural language descriptions. Our empirical results show that models trained on the data generated by MILP-Evolve achieve significant improvements on unseen problems, including MIPLIB benchmarks. Our work highlights the potential of moving towards a foundation model approach for MILP that can generalize to a broad range of MILP applications. Our code and data are publicly available at https://github.com/microsoft/OptiGuide.
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。