Publications

Combinatorial Optimization stuff

On Generalized Surrogate Duality in Mixed-Integer Nonlinear Programming. [doi] [pdf]
Benjamin Müller, Gonzalo Muñoz, Maxime Gasse, Ambros Gleixner, Andrea Lodi and Felipe Serrano
Mathematical Programming, vol. 192 (1), pp. 89-118, 2022

Ecole: A Gym-like Library for Machine Learning in Combinatorial Optimization Solvers. [pdf]
Antoine Prouvost, Justin Dumouchelle, Lara Scavuzzo, Maxime Gasse, Didier Chételat, Andrea Lodi
Learning Meets Combinatorial Algorithms NeurIPS Workshop (LMCA @ NeurIPS), 2020

Hybrid Models for Learning to Branch. [pdf]
Prateek Gupta, Maxime Gasse, Elias Khalil, Pawan K Mudigonda, Andrea Lodi, Yoshua Bengio
Neural Information Processing Systems (NeurIPS), 2020

On Generalized Surrogate Duality in Mixed-Integer Nonlinear Programming. [doi] [pdf]
Benjamin Müller, Gonzalo Muñoz, Maxime Gasse, Ambros Gleixner, Andrea Lodi and Felipe Serrano
21st Conference on Integer Programming and Combinatorial Optimization (IPCO), 2020

Exact Combinatorial Optimization with Graph Convolutional Neural Networks. [pdf]
Maxime Gasse, Didier Chételat, Nicola Ferroni, Laurent Charlin, Andrea Lodi
Neural Information Processing Systems (NeurIPS), 2019

Probabilistic Graphical Model stuff

On the Effectiveness of Two-Step Learning for Latent-Variable Models. [doi] [pdf]
Cem Subakan, Maxime Gasse and Laurent Charlin
IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP), 2020

Identifying the irreducible disjoint factors of a multivariate probability distribution. [pdf]
Maxime Gasse, Alex Aussem
International Conference on Probabilistic Graphical Models (PGM), pp. 183-194, 2016

A hybrid algorithm for Bayesian network structure learning with application to multi-label learning. [doi] [pdf]
Maxime Gasse, Alex Aussem, Haytham Elghazel
Expert Systems With Applications (ESWA), vol. 41 (15), pp. 6755-6772, 2014

Analysis of risk factors of hip fracture with causal Bayesian networks. [pdf]
Alex Aussem, Pascal Caillet, Zara Klemm, Maxime Gasse, Anne-Marie Schott and Michel Ducher
International Work-Conference on Bioinformatics and Biomedical Engineering (IWBBIO), pp. 1074-1085, 2014

An experimental comparison of hybrid algorithms for Bayesian network structure learning. [doi] [pdf]
Maxime Gasse, Alex Aussem, and Haytham Elghazel
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), pp. 58-73, 2012

Medical Imaging stuff

A Deep Learning Framework for Spatiotemporal Ultrasound Localization Microscopy. [doi]
Léo Milecki, Jonathan Porée, Hatim Belgharbi, Chloé Bourquin, Rafat Damseh, Patrick Delafontaine-Martel, Frédéric Lesage, Maxime Gasse, Jean Provost
IEEE Transactions on Medical Imaging (TMI), vol. 40 (5), pp. 1428-1437, 2021

Accelerating plane wave imaging through deep learning-based reconstruction: An experimental study. [doi]
Maxime Gasse, Fabien Millioz, Emmanuel Roux, Damien Garcia, Hervé Liebgott, Denis Friboulet
IEEE International Ultrasonics Symposium (IUS), 2017

High-Quality Plane Wave Compounding Using Convolutional Neural Networks. [doi] [pdf]
Maxime Gasse, Fabien Millioz, Emmanuel Roux, Damien Garcia, Hervé Liebgott, Denis Friboulet
IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control (TUFFC), vol. 64 (10), pp. 1637-1639, 2017

Multi-label Classification stuff

On the use of binary stochastic autoencoders for multi-label classification under the zero-one loss. [doi]
Denis Lecoeuche, Alex Aussem, Maxime Gasse
INNS Big Data and Deep Learning (INNS-BDDL), 2018

F-Measure Maximization in Multi-Label Classification with Conditionally Independent Label Subsets. [doi] [pdf]
Maxime Gasse, Alex Aussem
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), vol. 9851, pp. 619-631, 2016

On the Optimality of Multi-Label Classification under Subset Zero-One Loss for Distributions Satisfying the Composition Property. [pdf]
Maxime Gasse, Alex Aussem, Haytham Elghazel
International Conference on Machine Learning (ICML), pp. 2531-2539, 2015

PhD thesis

Probabilistic Graphical Model Structure Learning: Application to Multi-Label Classification. [pdf] [slides]
Maxime Gasse
PhD Thesis, Claude Bernard University Lyon 1, 2017

Other

Optimal Sensor Locations for Polymer Injection Molding Process. [doi]
David Garcia, Ronan Le Goff, Maxime Gasse, Alex Aussem
European Scientific Association for Material Forming (ESAFORM), pp. 1724-1733, 2014