arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.05697math.OC
收藏

面向混合整数线性优化的决策聚焦代理建模

Decision-Focused Surrogate Modeling for Mixed-Integer Linear Optimization

University of Minnesota Twin Cities(明尼苏达大学双城分校);ExxonMobil Technology and Engineering Company(埃克森美孚技术与工程公司)

Shivi Dixit, Rishabh Gupta, Qi Zhang

AI总结:

本文提出一种基于数据驱动的决策聚焦代理建模方法,通过构建线性规划模型高效求解混合整数线性规划问题,实现与原问题相近的最优解,且在两个案例中优于神经网络优化代理。

摘要:

混合整数优化是许多需要实时更新决策的在线决策系统的核心,但因其组合性质,混合整数线性规划(MILPs)难以求解,常无法满足时间敏感的在线应用需求。为解决这一挑战,我们开发了一种数据驱动的方法,构建以线性规划(LP)形式的代理优化模型,该模型比对应的MILPs更高效。我们以决策为导向训练这些代理LP,使得在不同模型输入下,其最优解与原MILPs相同或接近。该方法的一个关键优势是允许纳入原MILP的所有线性约束,显著提高了获得可行预测解的可能性。两个计算案例研究的结果表明,这种决策聚焦的代理建模方法具有高度的数据效率,并能提供非常准确的最优解预测。在这些例子中,它优于更常用的基于神经网络的优化代理。

英文摘要:

Mixed-integer optimization is at the core of many online decision-making systems that demand frequent updates of decisions in real time. However, due to their combinatorial nature, mixed-integer linear programs (MILPs) can be difficult to solve, rendering them often unsuitable for time-critical online applications. To address this challenge, we develop a data-driven approach for constructing surrogate optimization models in the form of linear programs (LPs) that can be solved much more efficiently than the corresponding MILPs. We train these surrogate LPs in a decision-focused manner such that for different model inputs, they achieve the same or close to the same optimal solutions as the original MILPs. One key advantage of the proposed method is that it allows the incorporation of all the original MILP's linear constraints, which significantly increases the likelihood of obtaining feasible predicted solutions. Results from two computational case studies indicate that this decision-focused surrogate modeling approach is highly data-efficient and provides very accurate predictions of the optimal solutions. In these examples, it outperforms more commonly used neural-network-based optimization proxies.

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。

↑