A central problem in unsupervised deep learning is how to find useful representations of
high-dimensional data, sometimes called" disentanglement." Most approaches are heuristic …

Mapping behavioural actions to neural activity is a fundamental goal of neuroscience. As our
ability to record large neural and behavioural data increases, there is growing interest in …

Self-supervised representation learning has shown remarkable success in a number of
domains. A common practice is to perform data augmentation via hand-crafted …

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 …

Contrastive learning has recently seen tremendous success in self-supervised learning. So
far, however, it is largely unclear why the learned representations generalize so effectively to …

An old problem in multivariate statistics is that linear Gaussian models are often
unidentifiable. In factor analysis, an orthogonal rotation of the factors is unidentifiable, while …

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 …

Understanding the latent causal factors of a dynamical system from visual observations is
considered a crucial step towards agents reasoning in complex environments. In this paper …

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 …

Unsupervised domain adaptation is critical to many real-world applications where label
information is unavailable in the target domain. In general, without further assumptions, the …