122 citations · 213 across the 20 of their papers we have counts for
20 papers
Identifiability of Potentially Degenerate Gaussian Mixture Models With Piecewise Affine Mixing
Danru Xu, Sébastien Lachapelle, Sara Magliacane
Causal representation learning (CRL) aims to identify the underlying latent variables from high-dimensional observations, even when variables are dependent with each other. We stud…
On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning
Sacha Morin, Moonsub Byeon, Alexia Jolicoeur-Martineau +1
Semi-supervised imitation learning (SSIL) consists in learning a policy from a small dataset of action-labeled trajectories and a much larger dataset of action-free trajectories. S…
On the Identifiability of Latent Action Policies
Sébastien Lachapelle
We study the identifiability of latent action policy learning (LAPO), a framework introduced recently to discover representations of actions from video data. We formally describe d…
Sparse Shift Autoencoders for Identifying Concepts from Large Language Model Activations
Shruti Joshi, Andrea Dittadi, Sébastien Lachapelle +1
Unsupervised approaches to large language model (LLM) interpretability, such as sparse autoencoders (SAEs), offer a way to decode LLM activations into interpretable and, ideally, c…
Causal Representation Learning in Temporal Data via Single-Parent Decoding
Philippe Brouillard, Sébastien Lachapelle, Julia Kaltenborn +6
Scientific research often seeks to understand the causal structure underlying high-level variables in a system. For example, climate scientists study how phenomena, such as El Niño…
All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling
Emanuele Marconato, Sébastien Lachapelle, Sebastian Weichwald +1
We analyze identifiability as a possible explanation for the ubiquity of linear properties across language models, such as the vector difference between the representations of "eas…
A Sparsity Principle for Partially Observable Causal Representation Learning
Danru Xu, Dingling Yao, Sébastien Lachapelle +4
Causal representation learning aims at identifying high-level causal variables from perceptual data. Most methods assume that all latent causal variables are captured in the high-d…
Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies
Sébastien Lachapelle, Pau Rodríguez López, Yash Sharma +4
This work introduces a novel principle for disentanglement we call mechanism sparsity regularization, which applies when the latent factors of interest depend sparsely on observed…
Multi-View Causal Representation Learning with Partial Observability
Dingling Yao, Danru Xu, Sébastien Lachapelle +5
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partial…
Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation
Sébastien Lachapelle, Divyat Mahajan, Ioannis Mitliagkas +1
We tackle the problems of latent variables identification and ``out-of-support'' image generation in representation learning. We show that both are possible for a class of decoders…
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning
Sébastien Lachapelle, Tristan Deleu, Divyat Mahajan +4
Although disentangled representations are often said to be beneficial for downstream tasks, current empirical and theoretical understanding is limited. In this work, we provide evi…
Partial Disentanglement via Mechanism Sparsity
Sébastien Lachapelle, Simon Lacoste-Julien
Disentanglement via mechanism sparsity was introduced recently as a principled approach to extract latent factors without supervision when the causal graph relating them in time is…
Typing assumptions improve identification in causal discovery
Philippe Brouillard, Perouz Taslakian, Alexandre Lacoste +2
Causal discovery from observational data is a challenging task that can only be solved up to a set of equivalent solutions, called an equivalence class. Such classes, which are oft…
Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA
Sébastien Lachapelle, Pau Rodríguez López, Yash Sharma +4
This work introduces a novel principle we call disentanglement via mechanism sparsity regularization, which can be applied when the latent factors of interest depend sparsely on pa…
On the Convergence of Continuous Constrained Optimization for Structure Learning
Ignavier Ng, Sébastien Lachapelle, Nan Rosemary Ke +2
Recently, structure learning of directed acyclic graphs (DAGs) has been formulated as a continuous optimization problem by leveraging an algebraic characterization of acyclicity. T…
Differentiable Causal Discovery from Interventional Data
Philippe Brouillard, Sébastien Lachapelle, Alexandre Lacoste +2
Learning a causal directed acyclic graph from data is a challenging task that involves solving a combinatorial problem for which the solution is not always identifiable. A new line…
Gradient-Based Neural DAG Learning
Sébastien Lachapelle, Philippe Brouillard, Tristan Deleu +1
We propose a novel score-based approach to learning a directed acyclic graph (DAG) from observational data. We adapt a recently proposed continuous constrained optimization formula…
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
Yoshua Bengio, Tristan Deleu, Nasim Rahaman +5
We propose to meta-learn causal structures based on how fast a learner adapts to new distributions arising from sparse distributional changes, e.g. due to interventions, actions of…
Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information
Eric Larsen, Sébastien Lachapelle, Yoshua Bengio +3
This paper offers a methodological contribution at the intersection of machine learning and operations research. Namely, we propose a methodology to quickly predict tactical soluti…
Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information
Eric Larsen, Sébastien Lachapelle, Yoshua Bengio +3
This paper offers a methodological contribution at the intersection of machine learning and operations research. Namely, we propose a methodology to quickly predict expected tactic…