Follow
Sébastien Lachapelle
Sébastien Lachapelle
Research scientist, Samsung's SAIT AI Lab, Montreal
Verified email at samsung.com - Homepage
Title
Cited by
Cited by
Year
A meta-transfer objective for learning to disentangle causal mechanisms
Y Bengio, T Deleu, N Rahaman, R Ke, S Lachapelle, O Bilaniuk, A Goyal, ...
arXiv preprint arXiv:1901.10912, 2019
4232019
Gradient-based neural dag learning
S Lachapelle, P Brouillard, T Deleu, S Lacoste-Julien
arXiv preprint arXiv:1906.02226, 2019
2892019
Differentiable causal discovery from interventional data
P Brouillard*, S Lachapelle*, A Lacoste, S Lacoste-Julien, A Drouin
Advances in Neural Information Processing Systems 33, 21865-21877, 2020
2142020
Disentanglement via mechanism sparsity regularization: A new principle for nonlinear ICA
S Lachapelle, P Rodriguez, Y Sharma, KE Everett, R Le Priol, A Lacoste, ...
Conference on Causal Learning and Reasoning, 428-484, 2022
1442022
Predicting tactical solutions to operational planning problems under imperfect information
E Larsen, S Lachapelle, Y Bengio, E Frejinger, S Lacoste-Julien, A Lodi
INFORMS Journal on Computing 34 (1), 227-242, 2022
90*2022
On the convergence of continuous constrained optimization for structure learning
I Ng, S Lachapelle, NR Ke, S Lacoste-Julien, K Zhang
International Conference on Artificial Intelligence and Statistics, 8176-8198, 2022
462022
Synergies between disentanglement and sparsity: Generalization and identifiability in multi-task learning
S Lachapelle*, T Deleu*, D Mahajan, I Mitliagkas, Y Bengio, ...
International Conference on Machine Learning, 18171-18206, 2023
442023
Multi-view causal representation learning with partial observability
D Yao, D Xu, S Lachapelle, S Magliacane, P Taslakian, G Martius, ...
arXiv preprint arXiv:2311.04056, 2023
292023
Partial disentanglement via mechanism sparsity
S Lachapelle, S Lacoste-Julien
arXiv preprint arXiv:2207.07732, 2022
282022
Additive decoders for latent variables identification and cartesian-product extrapolation
S Lachapelle*, D Mahajan*, I Mitliagkas, S Lacoste-Julien
Advances in Neural Information Processing Systems 36, 2024
272024
Nonparametric partial disentanglement via mechanism sparsity: Sparse actions, interventions and sparse temporal dependencies
S Lachapelle, PR López, Y Sharma, K Everett, RL Priol, A Lacoste, ...
arXiv preprint arXiv:2401.04890, 2024
212024
Typing assumptions improve identification in causal discovery
P Brouillard, P Taslakian, A Lacoste, S Lachapelle, A Drouin
Conference on Causal Learning and Reasoning, 162-177, 2022
192022
A sparsity principle for partially observable causal representation learning
D Xu, D Yao, S Lachapelle, P Taslakian, J Von Kügelgen, F Locatello, ...
arXiv preprint arXiv:2403.08335, 2024
112024
All or none: Identifiable linear properties of next-token predictors in language modeling
E Marconato, S Lachapelle, S Weichwald, L Gresele
arXiv preprint arXiv:2410.23501, 2024
22024
Identifiable Steering via Sparse Autoencoding of Multi-Concept Shifts
S Joshi, A Dittadi, S Lachapelle, D Sridhar
arXiv preprint arXiv:2502.12179, 2025
2025
Interaction Asymmetry: A General Principle for Learning Composable Abstractions
J Brady, J von Kügelgen, S Lachapelle, S Buchholz, T Kipf, W Brendel
arXiv preprint arXiv:2411.07784, 2024
2024
Causal Representation Learning in Temporal Data via Single-Parent Decoding
P Brouillard, S Lachapelle, J Kaltenborn, Y Gurwicz, D Sridhar, A Drouin, ...
arXiv preprint arXiv:2410.07013, 2024
2024
Sparsity regularization via tree-structured environments for disentangled representations
E Layne, J Hartford, S Lachapelle, M Blanchette, D Sridhar
arXiv preprint arXiv:2405.20482, 2024
2024
Leveraging Structure Between Environments: Phylogenetic Regularization Incentivizes Disentangled Representations
E Layne, D Sridhar, J Hartford, M Blanchette
UAI 2022 Workshop on Causal Representation Learning, 2024
2024
Causal Representation Learning
S Magliacane, A Mastakouri, YM Asano, C Shi, C Eastwood, S Lachapelle, ...
Annual Conference on Neural Information Processing Systems, 2023
2023
The system can't perform the operation now. Try again later.
Articles 1–20