Published:
SORTD computes the full Rashomon set of binary decision trees in anytime fashion.
Recommended citation: Arslan, E., van der Linden, J. G. M., Hoogendoorn, S. P., Rinaldi, M., & Demirović, E. (2025) "SORTeD Rashomon Sets of Sparse Decision Trees: Anytime Enumeration" Advances in NeurIPS-25, 44717-44755.
Download Paper | Source Repository
Published:
ConTree computes optimal binary classification trees on datasets with continuous features using dynamic programming with branch-and-bound.
Recommended citation: Brita, C. E., van der Linden, J. G. M., & Demirović, E. (2025). "Optimal Classification Trees for Continuous Feature Data Using Dynamic Programming with Branch-and-Bound." Proceedings of AAAI-25, 11131-11139.
Download Paper | Source Repository
Published:
STreeD is a DP framework that can optimize trees for a variety of objectives and constraints.
Recommended citation: Van der Linden, J. G. M., de Weerdt, M. M., & Demirović, E. (2023). "Necessary and Sufficient Conditions for Optimal Decision Trees Using Dynamic Programming." Advances in NeurIPS-23, 9173-9212.
Download Paper | Source Repository
Published:
DPF constructs fair and optimal binary classification trees. It minimizes misclassification score, while respecting a demographic parity fairness constraint, for a given size (depth, number of nodes). It can also generate the full Pareto front while optimizing both fairness and accuracy.
Recommended citation: Van der Linden, J. G. M., de Weerdt, M. M., & Demirović, E. (2022). "Fair and Optimal Decision Trees: A Dynamic Programming Approach." Advances in NeurIPS-22, 38899-38911.
Download Paper | Source Repository
Published:
TORS is an event-based simulator for the Train Unit Shunting and Servicing problem, which enables research on realistic applications of multi-agent pathfinding by providing users with a state, feasible actions, and real-time outcome calculations.
Recommended citation: Van der Linden, J. G. M., Mulderij, J., Huisman, B., den Ouden, J. W., van den Akker, M., Hoogeveen, H., & de Weerdt, M. M. (2021). "TORS: A Train Unit Shunting and Servicing Simulator." Proceedings of AAMAS-21, 1773-1775.
Download Paper | Source Repository
Published:
B-FELSA is a framework for benchmarking flexible electric load scheduling algorithms.
Recommended citation: Van der Linden, K., Romero, N., & de Weerdt, M. M. (2021). "Benchmarking Flexible Electric Loads Scheduling Algorithms." Energies 14(5), 1269.
Download Paper | Source Repository