Recent progress in Artificial Intelligence (AI) has demonstrated its power to tackle NP-hard discrete optimization problems and improve the decision-making process.
Numerous research articles have been published in both traditional Operations Research (OR) journals and top AI conferences, reflecting increasing interest in this emerging field.

This course is designed to prepare students to conduct their own research at the intersection of ML and discrete optimization.
We will focus primarily on scheduling and routing problems, graph optimization problems, and general mixed-integer programming (MIP). The course will cover two core topics:
(i) Data-driven algorithm design: Using AI to improve the performance of optimization algorithms
(ii) Data-driven optimization: Leveraging learned data to make better decisions under uncertainty.

Prerequisites
- IMEN662 Discrete Optimization (Strongly recommended)
- IMEN260 Operations Research I (or IMEN661 Advanced Linear Programming)
- IMEN272 Probability and Statistics for Engineers (or equivalent)
Recommended background
- IMEN764 Dynamic Programming & Reinforcement Learning Applications (or CSED627 Reinforcement Learning)
- Basic concepts in various machine learning models; only deep reinforcement learning and bandit models will be quickly reviewed, but not in detail

In-class presentation: 15%
Referee reports: 25%
Final project: 50%
Participation and attendance: 10%

Relevant courses in other schools
- Machine Learning for Discrete Optimization (Stanford University, MS&E236/CS225) by Prof. Ellen Vitercik in Spring 2024
- Machine Learning for Mathematical Optimization (University of Toronto, MIE1666H) by Prof. Elias B. Khalil in Fall 2021
- Topics in Discrete Optimization and Learning (University of Southern California CSCI 699) by Bistra Dilkina in Spring 2020
- Deep Learning in Discrete Optimization (University of Waterloo AMS 467/667) by William Cook in Spring 2018, 2020
- Robust Optimization (Politechnico di Milano, 061652) by Prof. Erick Hans Delage in Spring 2024

References
- Bengio, Y., Lodi, A., & Prouvost, A. (2021). Machine learning for combinatorial optimization: A methodological tour d’horizon. European Journal of Operational Research, 290(2), 405–421. https://doi.org/10.1016/j.ejor.2020.07.063
- Mazyavkina, N., Sviridov, S., Ivanov, S., & Burnaev, E. (2021). Reinforcement learning for combinatorial optimization: A survey. Computers & Operations Research, 134, 105400. https://doi.org/10.1016/j.cor.2021.105400
- Sadana, U., Chenreddy, A., Delage, E., Forel, A., Frejinger, E., & Vidal, T. (2024). A survey of contextual optimization methods for decision-making under uncertainty. European Journal of Operational Research. https://doi.org/10.1016/j.ejor.2024.03.020
- Mandi, J., Kotary, J., Berden, S., Mulamba, M., Bucarey, V., Guns, T., & Fioretto, F. (2024). Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities. Journal of Artificial Intelligence Research, 80, 1623–1701. https://doi.org/10.1613/jair.1.15320

* Part I: Basic machine learning techniques
Week 1: Introduction
Week 2: Deep Reinforcement Learning (DRL)
Week 3: Applications of DRL in Routing and Scheduling
Week 4: Simulation-based learning, Bandit models

* Part II: Data-driven Algorithm Design
Week 5: Learn-to-branch, Learn-to-cut
Week 6: Holiday
Week 7: Learning for Large Neighborhood Search (LNS)
Week 8: Learning for Branch & Price, and column generation
Week 9: INFORMS Annual Meeting 2025 (make-up theory classes for Part III)
Week 10: Learning for Branch & Price, and column generation (continued)
Week 11: Algorithms with prediction

* Part III: Data-driven optimization
Week 12: Optimization under uncertainty - theory
Week 13: Data-driven robust optimization
Week 14: Decision-focused learning

* Part IV: Finale
Week 15: Recent topics: Optimization over a trained neural network, Generative AI, and Explainable AI
Week 16: Final project presentation

The instructor will teach essential theoretical foundations and notable works in these fields. In addition to core lectures, students will actively engage through presenting research articles, writing referee reports, and completing a term project. Detailed course logistics will be provided in the syllabus. All classes and presentations will be conducted in English.

Auditors are also welcome, provided that they participate in class presentations and the term project.