Skip to main content
Article
Learning Latent Causal Dynamics
arXiv
  • Weiran Yao, Carnegie Mellon University
  • Guangyi Chen, Carnegie Mellon University & Mohamed bin Zayed University of Artificial Intelligence
  • Kun Zhang, Carnegie Mellon University & Mohamed bin Zayed University of Artificial Intelligence
Document Type
Article
Abstract

One critical challenge of time-series modeling is how to learn and quickly correct the model under unknown distribution shifts. In this work, we propose a principled framework, called LiLY, to first recover time-delayed latent causal variables and identify their relations from measured temporal data under different distribution shifts. The correction step is then formulated as learning the low-dimensional change factors with a few samples from the new environment, leveraging the identified causal structure. Specifically, the framework factorizes unknown distribution shifts into transition distribution changes caused by fixed dynamics and time-varying latent causal relations, and by global changes in observation. We establish the identifiability theories of nonparametric latent causal dynamics from their nonlinear mixtures under fixed dynamics and under changes. Through experiments, we show that time-delayed latent causal influences are reliably identified from observed variables under different distribution changes. By exploiting this modular representation of changes, we can efficiently learn to correct the model under unknown distribution shifts with only a few samples. © 2022, CC BY-NC-ND.

DOI
10.48550/arXiv.2202.04828
Publication Date
2-23-2022
Keywords
  • Causal relations; Critical challenges; Different distributions; Dimensional changes; Learn+; Low dimensional; Temporal Data; Time delayed; Time varying; Times series models
Comments

Preprint: arXiv

  • Archived with thanks to arXiv
  • Preprint License: CC by NC-ND
  • Uploaded 24 March 2022
Citation Information
W. Yao, G. Chen, and K. Zhang, "Learning latent causal dynamics," 2022, arXiv:arXiv:2202.04828v4