Thibaut Vidal's Projects
Source code of AC-DC-SBM, from "Assortative-Constrained Stochastic Block Models", Gribel, Vidal and Gendreau, ICPR 2020
Born-Again Tree Ensembles: Transforms a random forest into a single, minimal-size, tree with exactly the same prediction function in the entire feature space (ICML 2020).
Simple repository storing all the CVRP instances from the CVRPLib (accessible at http://vrp.galgos.inf.puc-rio.br/index.php/en/)
Source code associated with the paper "Optimal Decision Diagrams for Classification", authored by A.M. Florio, P. Martins, M. Schiffer, T. Serra, and T. Vidal, presented at AAAI 2023
Simple greedy algorithm (CART limited to a fixed depth) for decision tree construction. Used for the course INF2980 (Metaheuristics) in PUC-Rio.
Source code associated with the paper "Deep Learning for Data-Driven Districting-and-Routing", authored by A. Ferraz, Q. Cappart, and T. Vidal
DRAFT : Dataset Reconstruction Attack From Trained ensembles. Source code associated with the paper "Trained Random Forests Completely Reveal your Dataset (ICML'24, forthcoming)" authored by Julien Ferry, Ricardo Fukasawa, Timothée Pascal, and Thibaut Vidal
Source code associated with the paper "Free Lunch in the Forest: Functionally-Identical Pruning of Boosted Tree Ensembles" authored by Youssouf Emine, Alexandre Forel, Idriss Malek, and Thibaut Vidal
Code and data from the paper "Support Vector Machines with the Hard-Margin Loss: Optimal Training via Combinatorial Benders' Cuts" by I. Santana, B. Serrrano, M. Schiffer, and T. Vidal
Source code associated to the paper "Gribel, D., & Vidal, T. (2019). HG-means: A scalable hybrid metaheuristic for minimum sum-of-squares clustering. Pattern Recognition, 88, 569-583."
Hybrid Genetic Search for Arc Routing Problems. From "Node, edge, arc routing and turn penalties : Multiple problems - One neighborhood extension, Operations Research, 65(4), 2017", by Thibaut Vidal.
Modern implementation of the hybrid genetic search (HGS) algorithm specialized to the capacitated vehicle routing problem (CVRP). This code also includes an additional neighborhood called SWAP*.
Code and data from the paper: "Mecler, J., Subramanian, A., & Vidal, T. (2021). A simple and effective hybrid genetic search for the job sequencing and tool switching problem. Computers & Operations Research, 127, 105153."
Source code associated with the paper: "Vidal, T., Martinelli, R., Pham, T. A., & Hà, M. H. (2021). Arc routing with time-dependent travel times and paths. Transportation Science."
Code and data from the paper "Influence Optimization in Networks: New Formulations and Valid Inequalities", authored by V. Ferreira, A. Pessoa, and T. Vidal
OCEAN: Optimal Counterfactual Explanations in Tree Ensembles (ICML 2021)
This project contains the source code and data needed to reproduce all the experiments of the paper "Community Detection in the Stochastic Block Model by Mixed Integer Programming", authored by Breno Serrano and Thibaut Vidal
Code and data from the paper "Exponential-size neighborhoods for the pickup-and-delivery traveling salesman problem", authored by T. Pacheco, R. Martinelli, A. Subramanian, T. Toffolo, and T. Vidal
Library of Split algorithms, including the O(n) (linear time) algorithm for the CVRP, from "Vidal, Thibaut (2016). Technical note: Split algorithm in O(n) for the capacitated vehicle routing problem. Computers & Operations Research. 69, 40–47"