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

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 work …

Recent work has discussed the limitations of counterfactual explanations to recommend actions
for algorithmic recourse, and argued for the need of taking causal relationships between …

… Without further constraints on f, the pixel subsets Ik(z) and Ij(z) can overlap for any k ̸= j
such that latent slots k, j can affect the same pixels and thus contribute to generating the same …

Abstract Domain generalization (DG) seeks predictors which perform well on unseen test
distributions by leveraging data drawn from multiple related training distributions or domains. …

… Further, we say that Pj is a perfect intervention if the dependence of the j-th variable from its
parents is removed (pak(j) = ∅), corresponding to deleting all arrows pointing to i, sometimes …

Independent component analysis provides a principled framework for unsupervised
representation learning, with solid theory on the identifiability of the latent code that generated the …

… Xj for j 6= i. As discussed by Huang et al. [28], since E can be a common cause of variables
in X, causal … Each variable j in environment e has a randomly sampled mechanism …

An important component for generalization in machine learning is to uncover underlying latent
factors of variation as well as the mechanism through which each factor acts in the world. …

To avoid failures on out-of-distribution data, recent works have sought to extract features that
have an invariant or stable relationship with the label across domains, discarding" spurious…