← Authors

Sébastien Lachapelle

12 papers · 2020–2025 · 5 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌈 Renaissance Researcher (5) 🗺️ Taxonomy Completionist (16) 🌍 Conference Polyglot (5) 🏃 Academic Marathon (5) 🐝 Cross-Pollinator (11) 💎 Century Club (12) 🚀 Conference Pioneer

Conferences

ICLR (4) AISTATS (2) CLEAR (2) ICML (2) NIPS (2)

Top co-authors

Simon Lacoste-Julien (6) Tristan Deleu (3) Alexandre Lacoste (3) Philippe Brouillard (3) Julius von Kügelgen (3) Perouz Taslakian (3) Dingling Yao (2) Francesco Locatello (2) Ioannis Mitliagkas (2) Divyat Mahajan (2)

Keywords

causal discovery (3) independent component analysis (2) disentangled representation (2) sparse learning (1) structure learning (1) continuous optimization (1) group lasso (1) sparse feature learning (1) convergence guarantee (1) latent variable (1) normalizing flow (1) variational autoencoder (1) object-centric learning (1) latent factor (1) interventional datum (1) directed acyclic graph (1) observational datum (1) causal graph (1) equivalence class (1) augmented lagrangian method (1)

Papers

Interaction Asymmetry: A General Principle for Learning Composable Abstractions ICLR 2025
All or None: Identifiable Linear Properties of Next-Token Predictors in Language Modeling AISTATS 2025
Multi-View Causal Representation Learning with Partial Observability ICLR 2024
A Sparsity Principle for Partially Observable Causal Representation Learning ICML 2024
Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation NIPS 2023
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning ICML 2023
Typing assumptions improve identification in causal discovery CLEAR 2022
Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA CLEAR 2022
On the Convergence of Continuous Constrained Optimization for Structure Learning AISTATS 2022
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms ICLR 2020
Differentiable Causal Discovery from Interventional Data NIPS 2020
Gradient-Based Neural DAG Learning ICLR 2020