Causal normalizing flows: from theory to practice

Published: 21 Sept 2023, Last Modified: 02 Nov 2023NeurIPS 2023 oralEveryoneRevisionsBibTeX
Keywords: causality, causal inference, normalizing flows, identifiability, interventions, counterfactuals
TL;DR: Armed with identifiability results, we demonstraste how to use normalizing flows to capture a causal model and perform causal inference with it.
Abstract: In this work, we deepen on the use of normalizing flows for causal reasoning. Specifically, we first leverage recent results on non-linear ICA to show that causal models are identifiable from observational data given a causal ordering, and thus can be recovered using autoregressive normalizing flows (NFs). Second, we analyze different design and learning choices for *causal normalizing flows* to capture the underlying causal data-generating process. Third, we describe how to implement the *do-operator* in causal NFs, and thus, how to answer interventional and counterfactual questions. Finally, in our experiments, we validate our design and training choices through a comprehensive ablation study; compare causal NFs to other approaches for approximating causal models; and empirically demonstrate that causal NFs can be used to address real-world problems—where the presence of mixed discrete-continuous data and partial knowledge on the causal graph is the norm. The code for this work can be found at https://github.com/psanch21/causal-flows.
Supplementary Material: zip
Submission Number: 7006
Loading