-

 

 

 




Optimization Online





 

Mixed-Integer Optimization with Constraint Learning

Donato Maragno(d.maragno***at***uva.nl)
Holly Wiberg(hwiberg***at***mit.edu)
Dimitris Bertsimas(dbertsim***at***mit.edu)
S. Ilker Birbil(s.i.birbil***at***uva.nl)
Dick den Hertog(d.denhertog***at***uva.nl)
Adejuyigbe Fajemisin(a.o.fajemisin2***at***uva.nl)

Abstract: We establish a broad methodological foundation for mixed-integer optimization with learned constraints. We propose an end-to-end pipeline for data-driven decision making in which constraints and objectives are directly learned from data using machine learning, and the trained models are embedded in an optimization formulation. We exploit the mixed-integer optimization-representability of many machine learning methods, including linear models, decision trees, ensembles, and multi-layer perceptrons. The consideration of multiple methods allows us to capture various underlying relationships between decisions, contextual variables, and outcomes. We also characterize a decision trust region using the convex hull of the observations, to ensure credible recommendations and avoid extrapolation. We efficiently incorporate this representation using column generation and clustering. In combination with domain-driven constraints and objective terms, the embedded models and trust region define a mixed-integer optimization problem for prescription generation. We implement this framework as a Python package (OptiCL) for practitioners. We demonstrate the method in both chemotherapy optimization and World Food Programme planning. The case studies illustrate the benefit of the framework in generating high-quality prescriptions, the value added by the trust region, the incorporation of multiple machine learning methods, and the inclusion of multiple learned constraints.

Keywords: Mixed-Integer Optimization, Machine Learning, Constraint Learning, Prescriptive Analytics

Category 1: Integer Programming ((Mixed) Integer Linear Programming )

Category 2: Applications -- Science and Engineering (Data-Mining )

Category 3: Applications -- OR and Management Sciences

Citation: Massachusetts Institute of Technology and University of Amsterdam, November 2021

Download: [PDF]

Entry Submitted: 11/09/2021
Entry Accepted: 11/09/2021
Entry Last Modified: 11/09/2021

Modify/Update this entry


  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository

 

Submit
Update
Policies
Coordinator's Board
Classification Scheme
Credits
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society