Portrait de Quentin Cappart

Quentin Cappart

Membre affilié
Professeur agrégé, Polytechnique Montréal, Département de génie informatique et génie logiciel
Sujets de recherche
Apprentissage sur graphes
Raisonnement
Réseaux de neurones en graphes
Site web
Google Scholar
LinkedIn
X

Biographie

Quentin Cappart est professeur agrégé au Département de génie informatique et logiciel de Polytechnique Montréal et un membre affilié de Mila. Il a obtenu successivement un baccalauréat en ingénierie (2012), une M. Sc. en génie informatique (2014), une M. Sc. en gestion (2018) et un doctorat (2017) à l'Université catholique de Louvain (Belgique). Après son doctorat, il s’est joint à Polytechnique Montréal et au Centre interuniversitaire de recherche sur les réseaux d’entreprise, la logistique et le transport (CIRRELT) en tant que chercheur postdoctoral de 2018 à 2020. Pendant ces deux années, il a également été stagiaire en recherche chez ElementAI. Il dirige le groupe de recherche CORAIL, qu'il a cofondé avec le professeur Louis-Martin Rousseau. Ses recherches portent principalement sur l'intégration de l'apprentissage automatique à des procédures de recherche pour résoudre des problèmes combinatoires.

Étudiants actuels

Léo Boisvert
Doctorat - Polytechnique

Publications

Dynamic Routing and Wavelength Assignment with Reinforcement Learning.
Peyman Kafaei
Quentin Cappart
Nicolas Chapados
Hamed Pouya
Louis-Martin Rousseau
With the rapid developments in communication systems, and considering their dynamic nature, all-optical networks are becoming increasingly c… (voir plus)omplex. This study proposes a novel method based on deep reinforcement learning for the routing and wavelength assignment problem in all-optical wavelength-decision-multiplexing networks. We consider dynamic incoming requests, in which their arrival and holding times are not known in advance. The objective is to devise a strategy that minimizes the number of rejected packages due to the lack of resources in the long term. We use graph neural networks to capture crucial latent information from the graph-structured input to develop the optimal strategy. The proposed deep reinforcement learning algorithm selects a route and a wavelength simultaneously for each incoming traffic connection as they arrive. The results demonstrate that the learned agent outperforms the methods used in practice and can be generalized on network topologies that did not participate in training.
2023-12-31
INFORMS Journal on Optimization (publié)
doi.org
An Improved Neuro-Symbolic Architecture to Fine-Tune Generative AI Systems
Chao Yin
Quentin Cappart
Gilles Pesant
2023-12-31
Integration of AI and OR Techniques in Constraint Programming (publié)
doi.org
Learning Lagrangian Multipliers for the Travelling Salesman Problem
Augustin Parjadis
Quentin Cappart
Bistra Dilkina
Aaron M. Ferber
Louis-Martin Rousseau
2023-12-31
CP (publié)
doi.org
arxiv.org
Learning Precedences for Scheduling Problems with Graph Neural Networks
Hélène Verhaeghe
Quentin Cappart
Gilles Pesant
Claude-Guy Quimper
2023-12-31
CP (publié)
doi.org
Winning the 2023 CityLearn Challenge: A Community-Based Hierarchical Energy Systems Coordination Algorithm
Andoni I. Garmendia
Francesco Morri
Quentin Cappart
Hélène Le Cadre
. The effective management and control of building energy systems are crucial for reducing the energy consumption peak loads, CO 2 emissions… (voir plus), and ensuring the stability of the power grid, while maintaining optimal comfort levels within buildings. The difficulty to accommodate this trade-off is amplified by dynamic environmental conditions and the need for scalable solutions that can adapt across various building types and geographic locations. Acknowledging the importance of this problem, NeurIPS conference hosted since 2020 the CityLearn control challenge to foster the design of innovative solutions in building energy management. Participants were tasked with developing strategies that not only enhance energy efficiency but also prioritize sustainability and occupant comfort. This paper introduces the Community-based Hierarchical Energy Systems Co-ordination Algorithm ( CHESCA ), the winning approach of the 2023 edition. We rely on a hierarchical approach adaptable to an arbitrary number of buildings, first optimizing building-level metrics individually, and later refining these through a central community-level controller to improve grid-related metrics. Compared to the other high-ranked competitors, our approach demonstrated fast inference capabilities like learning-based methods, while offering a better interpretability and a superior generalization capabilities with minimal data requirements. This paper details our approach, supported by comprehensive experimental results and ablation studies.
2023-12-31
ECAI (publié)
doi.org
Decision Diagrams in Space!
Isaac Rudich
Quentin Cappart
Manuel L'opez-Ib'anez
Michael Romer
Louis-Martin Rousseau
2023-12-02
ArXiv (prépublication)
arxiv.org
arxiv.org
The Unsolved Challenges of LLMs as Generalist Web Agents: A Case Study
Rim Assouel
Tom Marty
Massimo Caccia
Issam Hadj Laradji
Alexandre Drouin
Sai Rajeswar
Hector Palacios
Quentin Cappart
David Vázquez
Nicolas Chapados
Maxime Gasse
Alexandre Lacoste
2023-11-06
NeurIPS.cc/2023/Workshop/FMDM (publié)
openreview.net
openreview.net
MARCO: A Memory-Augmented Reinforcement Framework for Combinatorial Optimization
Andoni I. Garmendia
Quentin Cappart
Josu Ceberio
Alexander Mendiburu
2023-08-18
Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence (publié)
doi.org
arxiv.org
The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights
Maxime Gasse
Simon Bowly
Quentin Cappart
Jonas Charfreitag
Laurent Charlin
Didier Chételat
Antonia Chmiela
Justin Dumouchelle
Ambros Gleixner
Aleksandr M. Kazachkov
Elias Khalil
Pawel Lichocki
Andrea Lodi
Miles Lubin
Chris J. Maddison
Christopher Morris
Dimitri J. Papageorgiou
Augustin Parjadis
Sebastian Pokutta
Antoine Prouvost … (voir 22 de plus)
Lara Scavuzzo
Giulia Zarpellon
Linxin Yang
Sha Lai
Akang Wang
Xiaodong Luo
Shuchang Zhou
Haohan Huang
Shengcheng Shao
Yuanming Zhu
Akang Wang
Mao Kun
Zixuan Cao
Yuanming Zhu
Zhewei Huang
Shuchang Zhou
C. Binbin
He Minggui
Hao Hao
Shuchang Zhou
Shuchang Zhou
Mao Kun
Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused … (voir plus)on solving problem instances in isolation, ignoring that they often stem from related data distributions in practice. However, recent years have seen a surge of interest in using machine learning as a new approach for solving combinatorial problems, either directly as solvers or by enhancing exact solvers. Based on this context, the ML4CO aims at improving state-of-the-art combinatorial optimization solvers by replacing key heuristic components. The competition featured three challenging tasks: finding the best feasible solution, producing the tightest optimality certificate, and giving an appropriate solver configuration. Three realistic datasets were considered: balanced item placement, workload apportionment, and maritime inventory routing. This last dataset was kept anonymous for the contestants.
2020-12-31
NeurIPS (Competition and Demos) (publié)
doi.org
proceedings.mlr.press