2023: Continuous cutting plane algorithms in integer programming, with Andrea Lodi, to appear in Operations Research Letters.
2023: Combinatorial optimization and reasoning with graph neural networks (Extended version), with Quentin Cappart, Elias B. Khalil, Andrea Lodi, Christopher Morris, Petar Veličković, published in Journal of Machine Learning Research 24, 1–61.
2022: Learning to branch with tree MDPs, with Lara Scavuzzo, Feng Y. Chen, Maxime Gasse, Andrea Lodi, Neil Yorke-Smith, Karen Aardal, published in Advances in Neural Information Processing Systems 35, 18514–18526.
2022: Learning to compare nodes in branch and bound with graph neural networks, with Abdel G. Labassi, Andrea Lodi, published in Advances in Neural Information Processing Systems 35, 32000–32010.
2022: Lookback for learning to branch, with Prateek Gupta, Elias B. Khalil, Maxime Gasse, Yoshua Bengio, Andrea Lodi, P. M. Kumar, published in Transactions on Machine Learning Research, November 2022.
2021: Combinatorial optimization and reasoning with graph neural networks, with Quentin Cappart, Elias B. Khalil, Andrea Lodi, Christopher Morris, Petar Veličković, published in International Joint Conference on Artificial Intelligence 30, 4348-4355.
2020: Ecole: A Gym-like library for machine learning in combinatorial optimization solvers, with Antoine Prouvost, Justin Dumouchelle, Maxime Gasse, Andrea Lodi, published in Learning Meets Combinatorial Algorithms Neurips Workshop.
2019: Exact combinatorial optimization with graph convolutional neural networks, with Maxime Gasse, Nicola Ferroni, Laurent Charlin, Andrea Lodi, published in Advances in Neural Information Processing Systems 32, 15554–15566.
2019: The middle-scale asymptotics of Wishart matrices, with Martin T. Wells, published in Annals of Statistics 47, 2639-2670.
2018: On the domain of attraction of a Tracy–Widom law with applications to testing multiple largest roots, with Rajendran Narayanan, Martin T. Wells, published in Journal of Multivariate Analysis 165, 132-142.
2017: Optimal two-step prediction in regression, with Joseph Salmon, Johannes Lederer, published in Electronic Journal of Statistics 11, 2519-2546.
2016: Improved second order estimation in the singular multivariate normal model, with Martin T. Wells, published in Journal of Multivariate Analysis 147, 1-19.
2012: Improved multivariate normal mean estimation with unknown covariance when p is greater than n, with Martin T. Wells, published in Annals of Statistics 40, 3137-3160.
Research Experience
Previously a researcher at the Canada Excellence Research Chair in Data Science for Real Time Decision Making; currently part of the graph deep learning team at Huawei’s Noah’s Ark Lab in Montreal.
Education
Ph.D. in Statistics from Cornell University in 2015, supervised by Martin T. Wells.
Background
A senior researcher at Huawei’s Noah’s Ark Lab in Montreal, Canada, focusing on graph deep learning, combinatorial optimization, and reasoning by intelligent agents.