Learning Linear Causal Representations from Interventions under General Nonlinear Mixing

Author name not available (Why is that?)

Publication date: 3 June 2023

Abstract: We study the problem of learning causal representations from unknown, latent interventions in a general setting, where the latent distribution is Gaussian but the mixing function is completely general. We prove strong identifiability results given unknown single-node interventions, i.e., without having access to the intervention targets. This generalizes prior works which have focused on weaker classes, such as linear maps or paired counterfactual data. This is also the first instance of causal identifiability from non-paired interventions for deep neural network embeddings. Our proof relies on carefully uncovering the high-dimensional geometric structure present in the data distribution after a non-linear density transformation, which we capture by analyzing quadratic forms of precision matrices of the latent distributions. Finally, we propose a contrastive algorithm to identify the latent variables in practice and evaluate its performance on various tasks.

Has companion code repository: https://github.com/simonbing/crlsanitycheck

This page was built for publication: Learning Linear Causal Representations from Interventions under General Nonlinear Mixing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6439133)