Abstract
IBM® ILOG® CP Optimizer (CPO) is a constraints solver that integrates multiple heuristics with the goal of handling a large diversity of combinatorial and scheduling problems while exposing a simple interface to users. CPO’s intent is to enable users to focus on problem modelling while automating the configuration of its optimization engine to solve the problem. For that purpose, CPO proposes an Auto search mode which implements a hard-coded logic to configure its search engine based on the runtime environment and some metrics computed on the input problem. This logic is the outcome of a mix of carefully designed rules and fine-tuning using experimental benchmarks. This paper explores the use of Machine Learning (ML) for the off-line configuration of CPO solver based on an analysis of problem instances. This data-driven effort has been motivated by the availability of a proprietary database of diverse benchmark problems that is used to evaluate and document CPO performance before each release. This work also addresses two methodological challenges: the ability of the trained predictive models to robustly generalize to the diverse set of problems that may be encountered in practice, and the integration of this new ML stage in the development workflow of the CPO product. Overall, this work resulted in a speedup improvement of about 14% (resp. 31%) on Combinatorial problems and about 5% (resp. 6%) on Scheduling problems when solving with 4 workers (resp. 8 workers), compared to the regular CPO solver.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Altmann, A., Tolosi, L., Sander, O., Lengauer, T.: Permutation importance: a corrected feature importance measure. Bioinformatics (Oxford, England) 26, 1340–1347 (2010). https://doi.org/10.1093/bioinformatics/btq134
Bengio, Y., Lodi, A., Prouvost, A.: Machine learning for combinatorial optimization: a methodological tour d’horizon. Eur. J. Oper. Res. 290, 405–421 (2021)
Hottung, A., Tierney, K.: Neural large neighborhood search for the capacitated vehicle routing problem. arXiv abs/1911.09539 (2020)
Karimi-Mamaghan, M., Mohammadi, M., Meyer, P., Karimi-Mamaghan, A.M., Talbi, E.G.: Machine learning at the service of meta-heuristics for solving combinatorial optimization problems: a state-of-the-art. Eur. J. Oper. Res. 296(2), 393–422 (2022)
Ke, G., et al.: LightGBM: a highly efficient gradient boosting decision tree. In: Advances in Neural Information Processing Systems, vol. 30, pp. 3146–3154 (2017)
Khalil, E.B., Morris, C., Lodi, A.: MIP-GNN: a data-driven framework for guiding combinatorial solvers. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 9, pp. 10219–10227 (2022). https://doi.org/10.1609/aaai.v36i9.21262. https://ojs.aaai.org/index.php/AAAI/article/view/21262
Kool, W., van Hoof, H., Welling, M.: Attention, learn to solve routing problems! In: ICLR (2019)
Kotary, J., Fioretto, F., Hentenryck, P.V., Wilder, B.: End-to-end constrained optimization learning: a survey. arXiv abs/2103.16378 (2021)
Kruber, M., Lübbecke, M.E., Parmentier, A.: Learning when to use a decomposition. In: CPAIOR (2017)
Laborie, P., Rogerie, J., Shaw, P., Vilím, P.: IBM ILOG CP optimizer for scheduling. Constraints 23(2), 210–250 (2018). https://doi.org/10.1007/s10601-018-9281-x
Microsoft: LightGBM documentation. https://lightgbm.readthedocs.io (2021)
Nogueira, F.: Bayesian Optimization: open source constrained global optimization tool for Python (2014). https://github.com/fmfn/BayesianOptimization
Smith-Miles, K., Lopes, L.: Measuring instance difficulty for combinatorial optimization problems. Comput. Oper. Res. 39, 875–889 (2012)
Tang, K., Liu, S., Yang, P., Yao, X.: Few-shots parallel algorithm portfolio construction via co-evolution. IEEE Trans. Evol. Comput. 25(3), 595–607 (2021)
Xu, L., Hutter, F., Hoos, H.H., Leyton-Brown, K.: SATzilla: portfolio-based algorithm selection for SAT. J. Artif. Intell. Res. 32, 565–606 (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Juillé, H., Dumeur, R., Shaw, P. (2023). Heuristics Selection with ML in CP Optimizer. In: Sellmann, M., Tierney, K. (eds) Learning and Intelligent Optimization. LION 2023. Lecture Notes in Computer Science, vol 14286. Springer, Cham. https://doi.org/10.1007/978-3-031-44505-7_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-44505-7_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44504-0
Online ISBN: 978-3-031-44505-7
eBook Packages: Computer ScienceComputer Science (R0)