PAC Learning of Causal Trees with Latent Variables

Authors

  • Prasad Tadepalli Oregon State University
  • Stuart J. Russell University of California at Berkeley

Keywords:

Causal Learning, Learning Theory, Active Learning, Probabilistic Graphical Models

Abstract

Learning causal models with latent variables from observational and experimental data is an important problem. In this paper we present a polynomial-time algorithm that PAC learns the structure and parameters of a rooted tree-structured causal network of bounded degree where the internal nodes of the tree cannot be observed or manipulated. Our algorithm is the first of its kind to provably learn the structure and parameters of tree-structured causal models with latent internal variables from random examples and active experiments.

Downloads

Published

2021-05-18

How to Cite

Tadepalli, P., & Russell, S. J. (2021). PAC Learning of Causal Trees with Latent Variables. Proceedings of the AAAI Conference on Artificial Intelligence, 35(11), 9774-9781. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17175

Issue

Section

AAAI Technical Track on Machine Learning IV