Causal representation learning seeks to extract high-level latent factors from low-level
sensory data. Most existing methods rely on observational data and structural assumptions …

We study causal representation learning, the task of inferring latent causal variables and
their causal relations from high-dimensional functions (“mixtures”) of the variables. Prior …

Causal disentanglement aims to uncover a representation of data using latent variables that
are interrelated through a causal model. Such a representation is identifiable if the latent …

Causal disentanglement seeks a representation of data involving latent variables that are
related via a causal model. A representation is identifiable if both the latent model and the …

Although disentangled representations are often said to be beneficial for downstream tasks,
current empirical and theoretical understanding is limited. In this work, we provide evidence …

The theory of representation learning aims to build methods that provably invert the data
generating process with minimal domain knowledge or any source of supervision. Most prior …

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 …

This paper studies the causal representation learning problem when the latent causal
variables are observed indirectly through an unknown linear transformation. The objectives …

This paper focuses on causal representation learning (CRL) under a general nonparametric
latent causal model and a general transformation model that maps the latent data to the …

This work introduces a novel principle for disentanglement we call mechanism sparsity
regularization, which applies when the latent factors of interest depend sparsely on …