Identifying Linearly-Mixed Causal Representations from Multi-Node Interventions

arXiv:2311.02695v2 Announce Type: replace-cross
Abstract: The task of inferring high-level causal variables from low-level observations, commonly referred to as causal representation learning, is fundamentally underconstrained. As such, recent works to address this problem focus on various assumptions that lead to identifiability of the underlying latent causal variables. A large corpus of these preceding approaches consider multi-environment data collected under different interventions on the causal model. What is common to virtually all of these works is the restrictive assumption that in …

abstract arxiv assumptions causal cs.lg focus low math.st mixed node representation representation learning stat.me stat.ml stat.th type variables