Linear causal disentanglement via higher-order cumulants
This addresses the problem of causal representation learning for researchers, providing theoretical guarantees for disentanglement under interventions, but it is incremental as it builds on existing methods.
The paper tackles the identifiability of linear causal disentanglement, showing that one perfect intervention per latent variable is sufficient and necessary to recover parameters, generalizing prior work to allow more latent than observed variables. For soft interventions, it characterizes the equivalence class of consistent latent graphs and parameters via polynomial equations, assuming non-Gaussian variables.
Linear causal disentanglement is a recent method in causal representation learning to describe a collection of observed variables via latent variables with causal dependencies between them. It can be viewed as a generalization of both independent component analysis and linear structural equation models. We study the identifiability of linear causal disentanglement, assuming access to data under multiple contexts, each given by an intervention on a latent variable. We show that one perfect intervention on each latent variable is sufficient and in the worst case necessary to recover parameters under perfect interventions, generalizing previous work to allow more latent than observed variables. We give a constructive proof that computes parameters via a coupled tensor decomposition. For soft interventions, we find the equivalence class of latent graphs and parameters that are consistent with observed data, via the study of a system of polynomial equations. Our results hold assuming the existence of non-zero higher-order cumulants, which implies non-Gaussianity of variables.