Sébastien Lachapelle
Ph.D. Student
Université de Montréal - DIRO
Mila
I am a second year Ph.D student supervised by Simon Lacoste-Julien
and Emma Frejinger.
I have graduated from Université de Montréal with a Bachelor's
degree in Mathematics and Economics.
I now work on causal structure learning, representation learning and ML applied to operations research.
More details can be found in my resume.
Publications & Preprints
- 5
Differentiable Causal Discovery from Interventional Data
By Philippe Brouillard*, Sébastien Lachapelle*, Alexandre Lacoste, Simon Lacoste-Julien and Alexandre Drouin.
*Equal contribution.
NeurIPS 2020 (Spotlight!).
- 4
On the Convergence of Continuous Constrained Optimization for Structure Learning
By Ignavier Ng, Sébastien Lachapelle, Nan Rosemary Ke and Simon Lacoste-Julien.
NeurIPS 2020 Workshop on Causal Discovery and Causality-Inspired Machine Learning (Oral!).
- 3
Gradient-Based Neural DAG Learning
By Sébastien Lachapelle, Philippe Brouillard, Tristan Deleu and Simon Lacoste-Julien.
ICLR 2020.
- 2
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.
- 1
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.
arXiv, last update: March 2019 (submitted to INFORMS Journal on Computing).
Orals & Posters
Science Talk at Element AI (2020) “Learning Causal Structures via Gradient-Based Optimization”, Montreal, Quebec, Canada.
NeurIPS 2019 Workshop on Solving Inverse Problems with Deep Networks “Gradient-Based Neural DAG Learning”, Vancouver, British-Columbia, Canada.
Montreal AI Symposium 2019 “Gradient-Based Neural DAG Learning”, Montreal, Quebec, Canada.
Deep Learning and Reinforcement Learning Summer School 2019 “Gradient-Based Neural DAG Learning”, Edmonton, Alberta, Canada.
Optimization Days 2018 “Predicting solution summaries to integer linear programs under imperfect information with machine learning”, Montreal, Quebec, Canada.
DIMACS 2018 “Predicting solution summaries to integer linear programs under imperfect information with machine learning", Bethlehem, Pennsylvania, United-States.
Contact
Sébastien Lachapelle
Mila - Quebec AI Institute
6666 Saint-Urbain
Montreal, QC
H2S 3H1 Canada
