Causal Representation Learning from General Environments under Nonparametric Mixing
Ng, Ignavier Xie, Shaoan Dong, Xinshuai Spirtes, Peter L. Zhang, Kun
Ng, Ignavier
Xie, Shaoan
Dong, Xinshuai
Spirtes, Peter L.
Zhang, Kun
Citations
Altmetric:
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Causal representation learning aims to recover the latent causal variables and their causal relations, typically represented by directed acyclic graphs (DAGs), from low-level observations such as image pixels. A prevailing line of research exploits multiple environments, which assume how data distributions change, including single-node interventions, coupled interventions, or hard interventions, or parametric constraints on the mixing function or the latent causal model, such as linearity. Despite the novelty and elegance of the results, they are often violated in real problems. Accordingly, we formalize a set of desiderata for causal representation learning that applies to a broader class of environments, referred to as general environments. Interestingly, we show that one can fully recover the latent DAG and identify the latent variables up to minor indeterminacies under a nonparametric mixing function and nonlinear latent causal models, such as additive (Gaussian) noise models or heteroscedastic noise models, by properly leveraging sufficient change conditions on the causal mechanisms up to third-order derivatives. These represent, to our knowledge, the first results to fully recover the latent DAG from general environments under nonparametric mixing. Notably, our results are stronger than many existing works, but require less restrictive assumptions about changing environments.
Citation
I. Ng, S. Xie, X. Dong, P. Spirtes, and K. Zhang, “Causal Representation Learning from General Environments under Nonparametric Mixing,” in Proc. 28th Int. Conf. Artif. Intell. Stat. (AISTATS 2025), vol. 258, Proc. Mach. Learn. Res., Mai Khao, Thailand, May 3–5, 2025, pp. 3700–3708.
Source
Proceedings of Machine Learning Research
Conference
28th International Conference on Artificial Intelligence and Statistics, AISTATS 2025
Keywords
Acyclic Graphs, Additive Gaussian Noise, Causal Modeling, Causal Relations, Data Distribution, Image Pixels, Latent Variable, Nonparametrics, Parametric Constraints, Real Problems, Mixing
Subjects
Source
28th International Conference on Artificial Intelligence and Statistics, AISTATS 2025
Publisher
ML Research Press