PySCIPOpt-ML: embedding trained machine learning models into mixed-integer programs

DOI10.1007/978-3-031-95976-9_14MaRDI QIDQ6897962zbMATH OpenFDO

Authors Mark G. Turner, Antonia Chmiela, Thorsten Koch, Michael Winkler

Publication date 19 November 2025

Full work available at URL https://doi.org/10.1007/978-3-031-95976-9_14

zbMATH Keywords

machine learning modelmixed-integer program

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Mixed integer programming (90C11) Combinatorial optimization (90C27)

Cites work

• A mixed integer approach for the transient case of gas network optimization.
• Algorithm AS 136: A K-Means Clustering Algorithm
• Between steps: intermediate relaxations between big-M and convex hull formulations
• Branch-and-cut for linear programs with overlapping SOS1 constraints
• Deep learning
• Deterministic global optimization with artificial neural networks embedded
• Empirical decision model learning
• scientific article; zbMATH DE number 7124428 (Why is no real title available?)
• JANOS: An Integrated Predictive and Prescriptive Modeling Framework
• JuMP 1.0: recent improvements to a modeling language for mathematical optimization
• Lossless compression of deep neural networks
• Mixed-Integer Convex Nonlinear Optimization with Gradient-Boosted Trees Embedded
• Pyomo -- optimization modeling in Python
• Scikit-learn: machine learning in Python
• Strong mixed-integer programming formulations for trained neural networks

Cited in

(1)

• Norm-induced cuts: outer approximation for Lipschitzian constraint functions

This page was built for publication: PySCIPOpt-ML: embedding trained machine learning models into mixed-integer programs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6897962)