{"type":"ScholarlyArticle","title":"Machine Learning for Integer Programming","authors":[{"name":"Elias B. Khalil","slug":"elias-b-khalil","given":"Elias B.","family":"Khalil","affiliation":""}],"abstract":"Mixed Integer Programs (MIP) are solved exactly by tree-based branch-and-bound search. However, various components of the algorithm involve making decisions that are currently addressed heuristically. Instead, I propose to use machine learning (ML) approaches such as supervised ranking and multi-armed bandits to make better-informed, input-specific decisions during MIP branch-and-bound. My thesis aims at improving the overall performance of MIP solvers. To illustrate the potential for ML in MIP, I have so far tackled branching variable selection, a crucial component of the search procedure, showing that ML approaches for variable selection can outperform traditional heuristics.","doi":null,"url":"https://ijcai.org/proceedings/2016/576","pdf":"https://ijcai.org/proceedings/2016/0576.pdf","markdown":"https://ijcai.org/proceedings/2016/576.md","bibtex":"https://ijcai.org/proceedings/2016/bibtex/576","volume":{"slug":"2016","title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2016","url":"https://ijcai.org/proceedings/2016/","year":2016,"location":"New York, NY, USA","dates":"9–15 July 2016","editors":"Subbarao Kambhampati","isbn":"978-1-57735-770-4; 978-1-57735-771-1","publisher":"AAAI Press / International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":576,"pages":{"first":4004,"last":4004},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}