A hybrid machine-learning and optimization method to solve bi-level problems

作者：

Highlights：

• Bilevel problem has many applications.

• It is an NP-hard problem, difficult to solve.

• Machine learning hybridized with traditional optimization method is developed.

• Numerical results of a real dataset are highly promising.

摘要

•Bilevel problem has many applications.•It is an NP-hard problem, difficult to solve.•Machine learning hybridized with traditional optimization method is developed.•Numerical results of a real dataset are highly promising.

论文关键词：Bi-level,Machine learning,Supervised learning,Discrete network design problem,Integer linear programming

论文评审过程：Received 6 October 2017, Revised 8 November 2017, Accepted 15 November 2017, Available online 16 November 2017, Version of Record 14 December 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.11.039