Combinatorial optimization and reasoning with graph neural networks

Q Cappart, D Chételat, EB Khalil, A Lodi… - Journal of Machine …, 2023 - jmlr.org
Combinatorial optimization is a well-established area in operations research and computer
science. Until recently, its methods have focused on solving problem instances in isolation …

A novel multi-attention reinforcement learning for the scheduling of unmanned shipment vessels (USV) in automated container terminals

J Zhu, W Zhang, L Yu, X Guo - Omega, 2024 - Elsevier
To improve the operating efficiency of container terminals, we investigate a closed-loop
scheduling method in an autonomous inter-terminal system that employs unmanned …

[HTML][HTML] Modelling Fresh and Dry Weight of Aboveground Biomass of Plant Community and Taxonomic Group Using Normalized Difference Vegetation Index and …

F Han, R Ding, Y Deng, X Zha, G Fu - Agronomy, 2024 - mdpi.com
In grassland ecosystems, aboveground biomass (AGB) is critical for energy flow, biodiversity
maintenance, carbon storage, climate regulation, and livestock husbandry. Particularly on …

[HTML][HTML] A machine-learning-based column generation heuristic for electric bus scheduling

J Gerbaux, G Desaulniers, Q Cappart - Computers & Operations Research, 2025 - Elsevier
Bus scheduling in public transit consists in determining a set of bus schedules to cover a set
of timetabled trips at minimum cost. This planning process has evolved recently with the …

Improved Peel-and-Bound: Methods for generating dual bounds with multivalued decision diagrams

I Rudich, Q Cappart, LM Rousseau - Journal of Artificial Intelligence …, 2023 - jair.org
Decision diagrams are an increasingly important tool in cutting-edge solvers for discrete
optimization. However, the field of decision diagrams is relatively new, and is still …

Decision diagram-based branch-and-bound with caching for dominance and suboptimality detection

V Coppé, X Gillard, P Schaus - INFORMS Journal on …, 2024 - pubsonline.informs.org
The branch-and-bound algorithm based on decision diagrams is a framework for solving
discrete optimization problems with a dynamic programming formulation. It works by …

Learning a generic value-selection heuristic inside a constraint programming solver

T Marty, T François, P Tessier, L Gauthier… - arxiv preprint arxiv …, 2023 - arxiv.org
Constraint programming is known for being an efficient approach for solving combinatorial
problems. Important design choices in a solver are the branching heuristics, which are …

A decision support method for credit risk based on the dynamic Bayesian network

J Lu, D Wu, J Dong, A Dolgui - Industrial Management & Data …, 2023 - emerald.com
Purpose Credit risk evaluation is a crucial task for banks and non-bank financial institutions
to support decision-making on granting loans. Most of the current credit risk methods rely …

Boosting Decision Diagram-Based Branch-And-Bound by Pre-Solving with Aggregate Dynamic Programming

V Coppé, X Gillard, P Schaus - 29th International Conference on …, 2023 - drops.dagstuhl.de
Discrete optimization problems expressible as dynamic programs can be solved by branch-
and-bound with decision diagrams. This approach dynamically compiles bounded-width …

Racing Control Variable Genetic Programming for Symbolic Regression

N Jiang, Y Xue - Proceedings of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
Symbolic regression, as one of the most crucial tasks in AI for science, discovers governing
equations from experimental data. Popular approaches based on genetic programming …