基于解预测的混合规划原解加速搜索
Accelerating Primal Solution Findings for Mixed Integer Programs Based on Solution Prediction
摘要:
混合规划(MIP)是求解组合优化问题最常用的建模方法之一。在许多应用中,一个类似的MIP模型定期求解,保持显着的相似性模型结构和解决方案的外观,但不同的配方系数。这为机器学习方法提供了探索模型结构与所得解值之间的相关性的机会。为了解决这个问题,我们提出了一个MIP实例,使用三分图,基于此构造一个图卷积网络(GCN)来预测解决方案的二进制变量的值。预测的解决方案被用来生成一个本地分支类型的削减,可以被视为一个全球性的(无效的)不平等的制定导致一个启发式的方法来解决MIP,或作为一个根分支规则导致一个确切的方法。对8种不同类型的MIP问题的计算评估表明,该框架显着提高了原始解决方案的性能上的最先进的开源MIP求解器。
英文摘要:
Mixed Integer Programming (MIP) is one of the most widely used modeling techniques for combinatorial optimization problems. In many applications, a similar MIP model is solved on a regular basis, maintaining remarkable similarities in model structures and solution appearances but differing in formulation coefficients. This offers the opportunity for machine learning methods to explore the correlations between model structures and the resulting solution values. To address this issue, we propose to represent an MIP instance using a tripartite graph, based on which a Graph Convolutional Network (GCN) is constructed to predict solution values for binary variables. The predicted solutions are used to generate a local branching type cut which can be either treated as a global (invalid) inequality in the formulation resulting in a heuristic approach to solve the MIP, or as a root branching rule resulting in an exact approach. Computational evaluations on 8 distinct types of MIP problems show that the proposed framework improves the primal solution finding performance significantly on a state-of-the-art open-source MIP solver.
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。