Polynomial-Time Algorithms for Counting and Sampling Markov Equivalent DAGs with Applications

Abstract

Counting and sampling directed acyclic graphs from a Markov equivalence class are fundamental tasks in graphical causal analysis. In this paper we show that these tasks can be performed in polynomial time, solving a long-standing open problem in this area. Our algorithms are effective and easily implementable. As we show in experiments, these breakthroughs make thought-to-be-infeasible strategies in active learning of causal structures and causal effect identification with regard to a Markov equivalence class practically applicable.

Cite

Text

Wienöbst et al. "Polynomial-Time Algorithms for Counting and Sampling Markov Equivalent DAGs with Applications." Journal of Machine Learning Research, 2023.

Markdown

[Wienöbst et al. "Polynomial-Time Algorithms for Counting and Sampling Markov Equivalent DAGs with Applications." Journal of Machine Learning Research, 2023.](https://mlanthology.org/jmlr/2023/wienobst2023jmlr-polynomialtime/)

BibTeX

@article{wienobst2023jmlr-polynomialtime,
  title     = {{Polynomial-Time Algorithms for Counting and Sampling Markov Equivalent DAGs with Applications}},
  author    = {Wienöbst, Marcel and Bannach, Max and Liśkiewicz, Maciej},
  journal   = {Journal of Machine Learning Research},
  year      = {2023},
  pages     = {1-45},
  volume    = {24},
  url       = {https://mlanthology.org/jmlr/2023/wienobst2023jmlr-polynomialtime/}
}