Research in Deep Constrained Learning (DCL) focuses on learning optimization problems featuring complex physical, engineering, and operational constraints. Target applications include energy systems and resilience. A key technical theme is the integration of optimization and machine learning techniques.
Recent Publications
- Spatial Network Decomposition for Fast and Scalable AC-OPF Learning. Minas Chatzos, Terrence Mak, and Pascal Van Hentenryck. IEEE Transactions on Power Systems (Early access: 10.1109/TPWRS.2021.3124726).
-
Combining Deep Learning and Optimization for Security-Constrained Optimal Power Flow. Alexandre Velloso and Pascal Van Hentenryck. IEEE Transactions on Power Systems, 36(4), July 2021.
- High-Fidelity Machine Learning Approximations of Large-Scale Optimal Power Flow, Minas Chatzos, Ferdinando Fioretto, Terrence W.K. Mak, Pascal Van Hentenryck, arXiv:2006.16356, June 2020.
- Lagrangian Duality for Constrained Deep Learning. Ferdinando Fioretto, Pascal Van Hentenryck, Terrence W.K. Mak, Cuong Tran, Federico Baldo and Michele Lombardi. In the Proceedings of 2020 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Ghent, Belgium, September 2020.
- Predicting AC Optimal Power Flows: Combining Deep Learning and Lagrangian Dual Methods. Ferdinando Fioretto, Terrence W.K. Mak, and Pascal Van Hentenryck. Proceeding of The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20).