End-to-End Constrained Optimization Learning: A Survey
End-to-End Constrained Optimization Learning: A Survey
复制标题
DOI：
10.24963/ijcai.2021/610
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
James Kotary;Ferdinando Fioretto;P. V. Hentenryck;Bryan Wilder
中科院分区：
文献类型：
--
作者：
James Kotary;Ferdinando Fioretto;P. V. Hentenryck;Bryan Wilder
本文综述了最近利用机器学习解决约束优化问题的尝试。它侧重于调查将组合求解器和优化方法与机器学习架构集成的工作。这些方法有望开发新的混合机器学习和优化方法，以预测组合问题的快速近似解决方案，并实现结构逻辑推理。本文提出了一个概念性的审查，在这一新兴领域的最新进展。
This paper surveys the recent attempts at leveraging machine learning to solve constrained optimization problems. It focuses on surveying the work on integrating combinatorial solvers and optimization methods with machine learning architectures. These approaches hold the promise to develop new hybrid machine learning and optimization methods to predict fast, approximate, solutions to combinatorial problems and to enable structural logical inference. This paper presents a conceptual review of the recent advancements in this emerging area.