Sébastien Lachapelle
Research Scientist at SAIT AI Lab (Samsung)
Watch my Ph.D. defense
Selected Publications & Preprints
Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies
By Sébastien Lachapelle, Pau Rodríguez López , Yash Sharma , Katie Everett , Rémi Le Priol , Alexandre Lacoste and Simon Lacoste-Julien.
Preprint.
Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation
By Sébastien Lachapelle*, Divyat Mahajan*, Ioannis Mitliagkas and Simon Lacoste-Julien.
*Equal contributions.
NeurIPS 2023 (Oral!).
Synergies Between Disentanglement and Sparsity: a Multi-Task Learning Perspective
By Sébastien Lachapelle*, Tristan Deleu*, Divyat Mahajan, Ioannis Mitliagkas, Yoshua Bengio, Simon Lacoste-Julien and Quentin Bertrand.
*Equal contributions.
ICML 2023.
Partial Disentanglement via Mechanism Sparsity
By Sébastien Lachapelle and Simon Lacoste-Julien.
UAI 2022 First Workshop on Causal Representation Learning (Workshop oral + Best paper award!).
Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA
By Sébastien Lachapelle, Pau Rodríguez López , Yash Sharma , Katie Everett , Rémi Le Priol , Alexandre Lacoste and Simon Lacoste-Julien.
CLeaR 2022.
Typing assumptions improve identification in causal discovery
By Philippe Brouillard, Perouz Taslakian, Alexandre Lacoste, Sébastien Lachapelle and Alexandre Drouin.
CLeaR 2022 (Oral!).
Differentiable Causal Discovery from Interventional Data
By Philippe Brouillard*, Sébastien Lachapelle*, Alexandre Lacoste, Simon Lacoste-Julien and Alexandre Drouin.
*Equal contribution.
NeurIPS 2020 (Spotlight!).
On the Convergence of Continuous Constrained Optimization for Structure Learning
By Ignavier Ng, Sébastien Lachapelle, Nan Rosemary Ke and Simon Lacoste-Julien.
AISTATS 2022.
ICML 2021 Workshop on The Neglected Assumptions in Causal Inference 2022 (Workshop oral!).
Gradient-Based Neural DAG Learning
By Sébastien Lachapelle, Philippe Brouillard, Tristan Deleu and Simon Lacoste-Julien.
ICLR 2020.
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
By Yoshua Bengio, Tristan Deleu, Nasim Rahaman, Rosemary Ke, Sébastien Lachapelle, Olexa Bilaniuk, Anirudh Goyal and Christopher Pal.
ICLR 2020.
Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information
By Eric Larsen, Sébastien Lachapelle, Yoshua Bengio, Emma Frejinger, Simon Lacoste-Julien and Andrea Lodi.
INFORMS Journal on Computing 2021.
Contact
Sébastien Lachapelle
Mila - Quebec AI Institute
6666 Saint-Urbain
Montreal, QC
H2S 3H1 Canada