Learning to Handle Parameter Perturbations in Combinatorial Optimization: an Application to Facility Location

We present an approach to couple the resolution of Combinatorial Optimization problems with methods from Machine Learning, applied to the single source, capacitated, facility location problem. Our study is framed in the context where a reference facility location optimization problem is given. Assuming there exist data for many variations of the reference problem (historical or simulated) along with their optimal solution, we study how one can exploit these to make predictions about an unseen new instance. We demonstrate how a classifier can be built from these data to determine whether the solution to the reference problem still applies to a new instance. In case the reference solution is partially applicable, we build a regressor indicating the magnitude of the expected change, and conversely how much of it can be kept for the new instance. This insight, derived from a priori information, is expressed via an additional constraint in the original mathematical programming formulation. We present an empirical evaluation and discuss the benefits, drawbacks and perspectives of such an approach. Although presented through the application to the facility location problem, the approach developed here is general and explores a new perspective on the exploitation of past experience in combinatorial optimization.

[1]  Feng Qiu,et al.  Learning to Solve Large-Scale Security-Constrained Unit Commitment Problems , 2019, INFORMS J. Comput..

[2]  Le Song,et al.  2 Common Formulation for Greedy Algorithms on Graphs , 2018 .

[3]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[4]  Le Song,et al.  Learning to Branch in Mixed Integer Programming , 2016, AAAI.

[5]  Alexandre Lacoste,et al.  Learning Heuristics for the TSP by Policy Gradient , 2018, CPAIOR.

[6]  Maria Grazia Speranza,et al.  Kernel search for the capacitated facility location problem , 2012, J. Heuristics.

[7]  Andreas Drexl,et al.  Facility location models for distribution system design , 2005, Eur. J. Oper. Res..

[8]  Marco Fraccaro,et al.  Machine learning meets mathematical optimization to predict the optimal production of offshore wind parks , 2018, Comput. Oper. Res..

[9]  Andrea Lodi,et al.  Learning a Classification of Mixed-Integer Quadratic Programming Problems , 2017, CPAIOR.

[10]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[11]  Quoc V. Le,et al.  Neural Optimizer Search with Reinforcement Learning , 2017, ICML.

[12]  Alberto Ceselli,et al.  Random sampling and machine learning to understand good decompositions , 2018, Ann. Oper. Res..

[13]  Benjamin Müller,et al.  The SCIP Optimization Suite 5.0 , 2017, 2112.08872.

[14]  Maria Grazia Speranza,et al.  A heuristic for BILP problems: The Single Source Capacitated Facility Location Problem , 2014, Eur. J. Oper. Res..

[15]  Yuri Malitsky,et al.  DASH: Dynamic Approach for Switching Heuristics , 2013, Eur. J. Oper. Res..

[16]  Andrea Lodi,et al.  On learning and branching: a survey , 2017 .

[17]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[18]  Yoshua Bengio,et al.  Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon , 2018, Eur. J. Oper. Res..

[19]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[20]  Louis Wehenkel,et al.  A Machine Learning-Based Approximation of Strong Branching , 2017, INFORMS J. Comput..

[21]  Yoshua Bengio,et al.  Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information , 2018, INFORMS J. Comput..

[22]  D. Ruppert The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[23]  Marco E. Lübbecke,et al.  Learning When to Use a Decomposition , 2017, CPAIOR.

[24]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[25]  George L. Nemhauser,et al.  The uncapacitated facility location problem , 1990 .

[26]  He He,et al.  Learning to Search in Branch and Bound Algorithms , 2014, NIPS.

[27]  Matteo Fischetti,et al.  Local branching , 2003, Math. Program..

[28]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[29]  Yoshua Bengio,et al.  Predicting Solution Summaries to Integer Linear Programs under Imperfect Information with Machine Learning , 2018, ArXiv.