The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights

Maxime Gasse, Simon Bowly, Quentin Cappart, Jonas Charfreitag, Laurent Charlin, Didier Chételat, Antonia Chmiela, Justin Dumouchelle, Ambros Gleixner, Aleksandr M. Kazachkov, Elias Khalil, Pawel Lichocki, Andrea Lodi, Miles Lubin, Chris J. Maddison, Morris Christopher, Dimitri J. Papageorgiou, Augustin Parjadis, Sebastian Pokutta, Antoine Prouvost, Lara Scavuzzo, Giulia Zarpellon, Linxin Yang, Sha Lai, Akang Wang, Xiaodong Luo, Xiang Zhou, Haohan Huang, Shengcheng Shao, Yuanming Zhu, Dong Zhang, Tao Quan, Zixuan Cao, Yang Xu, Zhewei Huang, Shuchang Zhou, Chen Binbin, He Minggui, Hao Hao, Zhang Zhiyu, An Zhiwu, Mao Kun
Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, PMLR 176:220-231, 2022.

Abstract

Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused on solving problem instances in isolation, ignoring that they often stem from related data distributions in practice. However, recent years have seen a surge of interest in using machine learning as a new approach for solving combinatorial problems, either directly as solvers or by enhancing exact solvers. Based on this context, the ML4CO aims at improving state-of-the-art combinatorial optimization solvers by replacing key heuristic components. The competition featured three challenging tasks: finding the best feasible solution, producing the tightest optimality certificate, and giving an appropriate solver configuration. Three realistic datasets were considered: balanced item placement, workload apportionment, and maritime inventory routing. This last dataset was kept anonymous for the contestants.

Cite this Paper

BibTeX
@InProceedings{pmlr-v176-gasse22a, title = {The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights}, author = {Gasse, Maxime and Bowly, Simon and Cappart, Quentin and Charfreitag, Jonas and Charlin, Laurent and Ch{\'e}telat, Didier and Chmiela, Antonia and Dumouchelle, Justin and Gleixner, Ambros and Kazachkov, Aleksandr M. and Khalil, Elias and Lichocki, Pawel and Lodi, Andrea and Lubin, Miles and Maddison, Chris J. and Christopher, Morris and Papageorgiou, Dimitri J. and Parjadis, Augustin and Pokutta, Sebastian and Prouvost, Antoine and Scavuzzo, Lara and Zarpellon, Giulia and Yang, Linxin and Lai, Sha and Wang, Akang and Luo, Xiaodong and Zhou, Xiang and Huang, Haohan and Shao, Shengcheng and Zhu, Yuanming and Zhang, Dong and Quan, Tao and Cao, Zixuan and Xu, Yang and Huang, Zhewei and Zhou, Shuchang and Binbin, Chen and Minggui, He and Hao, Hao and Zhiyu, Zhang and Zhiwu, An and Kun, Mao}, booktitle = {Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track}, pages = {220--231}, year = {2022}, editor = {Kiela, Douwe and Ciccone, Marco and Caputo, Barbara}, volume = {176}, series = {Proceedings of Machine Learning Research}, month = {06--14 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v176/gasse22a/gasse22a.pdf}, url = {https://proceedings.mlr.press/v176/gasse22a.html}, abstract = {Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused on solving problem instances in isolation, ignoring that they often stem from related data distributions in practice. However, recent years have seen a surge of interest in using machine learning as a new approach for solving combinatorial problems, either directly as solvers or by enhancing exact solvers. Based on this context, the ML4CO aims at improving state-of-the-art combinatorial optimization solvers by replacing key heuristic components. The competition featured three challenging tasks: finding the best feasible solution, producing the tightest optimality certificate, and giving an appropriate solver configuration. Three realistic datasets were considered: balanced item placement, workload apportionment, and maritime inventory routing. This last dataset was kept anonymous for the contestants.} }
Endnote
%0 Conference Paper %T The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights %A Maxime Gasse %A Simon Bowly %A Quentin Cappart %A Jonas Charfreitag %A Laurent Charlin %A Didier Chételat %A Antonia Chmiela %A Justin Dumouchelle %A Ambros Gleixner %A Aleksandr M. Kazachkov %A Elias Khalil %A Pawel Lichocki %A Andrea Lodi %A Miles Lubin %A Chris J. Maddison %A Morris Christopher %A Dimitri J. Papageorgiou %A Augustin Parjadis %A Sebastian Pokutta %A Antoine Prouvost %A Lara Scavuzzo %A Giulia Zarpellon %A Linxin Yang %A Sha Lai %A Akang Wang %A Xiaodong Luo %A Xiang Zhou %A Haohan Huang %A Shengcheng Shao %A Yuanming Zhu %A Dong Zhang %A Tao Quan %A Zixuan Cao %A Yang Xu %A Zhewei Huang %A Shuchang Zhou %A Chen Binbin %A He Minggui %A Hao Hao %A Zhang Zhiyu %A An Zhiwu %A Mao Kun %B Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track %C Proceedings of Machine Learning Research %D 2022 %E Douwe Kiela %E Marco Ciccone %E Barbara Caputo %F pmlr-v176-gasse22a %I PMLR %P 220--231 %U https://proceedings.mlr.press/v176/gasse22a.html %V 176 %X Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused on solving problem instances in isolation, ignoring that they often stem from related data distributions in practice. However, recent years have seen a surge of interest in using machine learning as a new approach for solving combinatorial problems, either directly as solvers or by enhancing exact solvers. Based on this context, the ML4CO aims at improving state-of-the-art combinatorial optimization solvers by replacing key heuristic components. The competition featured three challenging tasks: finding the best feasible solution, producing the tightest optimality certificate, and giving an appropriate solver configuration. Three realistic datasets were considered: balanced item placement, workload apportionment, and maritime inventory routing. This last dataset was kept anonymous for the contestants.
APA
Gasse, M., Bowly, S., Cappart, Q., Charfreitag, J., Charlin, L., Chételat, D., Chmiela, A., Dumouchelle, J., Gleixner, A., Kazachkov, A.M., Khalil, E., Lichocki, P., Lodi, A., Lubin, M., Maddison, C.J., Christopher, M., Papageorgiou, D.J., Parjadis, A., Pokutta, S., Prouvost, A., Scavuzzo, L., Zarpellon, G., Yang, L., Lai, S., Wang, A., Luo, X., Zhou, X., Huang, H., Shao, S., Zhu, Y., Zhang, D., Quan, T., Cao, Z., Xu, Y., Huang, Z., Zhou, S., Binbin, C., Minggui, H., Hao, H., Zhiyu, Z., Zhiwu, A. & Kun, M.. (2022). The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights. Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, in Proceedings of Machine Learning Research 176:220-231 Available from https://proceedings.mlr.press/v176/gasse22a.html.

Related Material