I am research sofware engineer in combinatorial optimization and machine learning working at Artelys, in Paris.

I graduated with Ph.D. in Machine Learning for Combinatorial Optimization from Polytechnique Montréal under supervison of Prof. Andrea Lodi at CERC DS4DM and Prof. Yoshua Bengio at Mila. I worked at the interplay of deep learning and operations research, building combinatorial optimization algorithm that leverage machine learning to adapt to different problem structure. During my Ph.D., I lead the development of Ecole, a Python and C++ library that aims to expose a number of control problems arising in combinatorial optimization solvers as Markov Decision Processes (i.e., Reinforcement Learning environments).

Before the Ph.D., I obtained an engineering degree (M.Sc.) in Data Science from École Polytechnique, France’s leading engineering school.

I am passionate about software engineering and design. From safe and performant code, to continuous testing, packaging, adn deployment. I am grateful for all the open-source tools that helped me along the way. I try to give back when I can and to advocate for open code around me.

Interests: Deep Learning, Reinforcement Learning, Discrete Optimization, Software Engineering.

Publications

2021

• Ecole: A Library for Learning Inside MILP Solvers. Antoine Prouvost, Justin Dumouchelle, Maxime Gasse, Didier Chételat, Andrea Lodi. Under review in INFORMS Journal of Computing.
  [pdf] [website] [code]

2020

• Ecole: A Gym-like Library for Machine Learning in Combinatorial Optimization Solvers. Antoine Prouvost, Justin Dumouchelle, Lara Scavuzzo, Maxime Gasse, Didier Chételat, Andrea Lodi. Poster paper in NeurIPS Learning Meets Combinatorial Algorithm Workshop.
  [pdf] [website] [code]
• Machine learning for combinatorial optimization: A methodological tour d’horizon. Yoshua Bengio, Andrea Lodi, Antoine Prouvost. European Journal of Operations Research.
  [pdf]
• Adverse Event Prediction by Telemonitoring and Deep Learning. Antoine Prouvost, Andrea Lodi, Louis-Martin Rousseau, and Jonathan Vallee. Fourth International Conference on Health Care Systems Engineering.
  [pdf] [bib]

Research Presentations

2021

• Recent Advances in Integrating Machine Learning and Combinatorial Optimization Elias B. Khalil, Andrea Lodi, Bistra Dilkina, Didier Chételat, Maxime Gasse, Antoine Prouvost, Giulia Zarpellon, Laurent Charlin Tutorial in AAAI, Online.
• Machine Learning for Combinatorial Optimization. Elias B. Khalil, Didier Chételat, Maxime Gasse, Antoine Prouvost, Giulia Zarpellon, Laurent Charlin, Andrea Lodi. Tutorial in IJCAI 2020, Online, Postponed.
• Ecole: A Library for Learning Inside MILP Solvers. Antoine Prouvost, Justin Dumouchelle, Maxime Gasse, Didier Chételat, Andrea Lodi. Talk in INFORMS, Anaheim.

2020

• Ecole: A Gym-like Library for Machine Learning in Combinatorial Optimization Solvers. Antoine Prouvost, Justin Dumouchelle, Lara Scavuzzo, Maxime Gasse, Didier Chételat, Andrea Lodi. Poster in NeurIPS LMCA Workshop, Online.
• Ecole: A Library for Learning Inside MILP Solvers. Antoine Prouvost, Justin Dumouchelle, Maxime Gasse, Didier Chételat, Andrea Lodi. Talk in INFORMS, Online.

2019

• Learning a Cutting Plane Selection Policy. Antoine Prouvost, Maxime Gasse, Didier Chetelat, Andrea Lodi.
  Talk in INFORMS, Seattle.
• Learning a Cutting Plane Selection Policy. Antoine Prouvost, Aleksandr M. Kazachkov, Andrea Lodi.
  Poster in MIP workshop, Boston.
• Adverse Event Prediction by Telemonitoring and Deep Learning. Antoine Prouvost, Andrea Lodi, Louis-Martin Rousseau, Jonathan Valle.
  Talk in HCSE, Montreal.
• Machine Learning for Combinatorial Optimization. Antoine Prouvost, Yoshua Bengio, Andrea Lodi.
  Talk in Optimization Days, Montreal.
• Machine Learning for Combinatorial Optimization. Antoine Prouvost, Yoshua Bengio, Andrea Lodi.
  Talk at ElementAI headquarters, Montreal.

2018

• Methodology of Machine Learning for Combinatorial Optimization. Antoine Prouvost, Andrea Lodi. Student talk at CERMICS Operations Research and Machine Learning summer school. Fréjus.

Community Events

2021

• NeurIPS Machine Learning for Combinatorial Optimization Competition. Simon Bowly, Chris Cameron, Quentin Cappart, Jonas Charfreitag, Laurent Charlin, Didier Chételat, Justin Dumouchelle, Maxime Gasse, Ambros Gleixner, Aleksandr M. Kazachkov, Elias B. Khalil, Pawel Lichocki, Andrea Lodi, Miles Lubin, Chris J. Maddison, Christopher Morris, Dimitri J. Papageorgiou, Augustin Parjadis, Sebastian Pokutta, Antoine Prouvost, Lara Scavuzzo, Giulia Zarpellon.
  Co-organiser, Ecole support.

Engineering Tutorials

• Organizing a Python Project at GERAD (Feb 2020).
• Introduction to PyTorch at GERAD (Sep 2018), Mila (Nov 2018, Jan 2019), NextAi (Mar 2019, Mar 2020). [code]
• Git and Github at GERAD (May 2018).