Causal normalizing flows: From theory to practice

Adrian Javaloy, Pablo Sánchez-Martín, Isabel Valera

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 36 (NeurIPS 2023)
EditorsAlice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, Sergey Levine
PublisherNeural Information Processing Systems Foundation (NeurIPS)
Pages1-32
Number of pages32
ISBN (Electronic)9781713899921
Publication statusPublished - 16 Dec 2023
EventThirty-Seventh Conference on Neural Information Processing Systems - New Orleans Ernest N. Morial Convention Center, New Orleans, United States
Duration: 10 Dec 202316 Dec 2023
Conference number: 37
https://neurips.cc/Conferences/2023

Publication series

NameAdvances in Neural Information Processing Systems
PublisherNeurIPS
ISSN (Print)1049-5258

Conference

ConferenceThirty-Seventh Conference on Neural Information Processing Systems
Abbreviated titleNeurIPS 2023
Country/TerritoryUnited States
CityNew Orleans
Period10/12/2316/12/23
Internet address

Keywords / Materials (for Non-textual outputs)

  • machine learning
  • artificial intelligence
  • methodology

Fingerprint

Dive into the research topics of 'Causal normalizing flows: From theory to practice'. Together they form a unique fingerprint.

Cite this