Machine learning for combinatorial optimization: A methodological tour d'horizon

作者：Yoshua Bengio, Andrea Lodi, Antoine Prouvost · 发表于：Archivio istituzionale della ricerca (Alma Mater Studiorum Università di Bologna) · 年份：2021 · DOI：10.1016/j.ejor.2020.07.063 · 被引用次数：1443 · 研究领域：Scheduling and Optimization Algorithms、Constraint Satisfaction and Optimization、Metaheuristic Optimization Algorithms Research

This paper surveys the recent attempts, both from the machine learning and operations research communities, at leveraging machine learning to solve combinatorial optimization problems. Given the hard nature of these problems, state-of-the-art algorithms rely on handcrafted heuristics for making decisions that are otherwise too expensive to compute or mathematically not well defined. Thus, machine learning looks like a natural candidate to make such decisions in a more principled and optimized way. We advocate for pushing further the integration of machine learning and combinatorial optimization and detail a methodology to do so. A main point of the paper is seeing generic optimization problems as data points and inquiring what is the relevant distribution of problems to use for learning on a given task.