This repository provides code for the methods LHTS, NHTS, and ED and experimental setup developed in the paper:

Hybrid Top-Down Global Causal Discovery with Local Search for Linear and Nonlinear Additive Noise Models
Authors: Sujai Hiremath, Jacqueline R. M. A. Maasch, Mengxiao Gao, Promit Ghosal, and Kyra Gan
Conference: The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)

---

If you find this paper/code useful in your research, we kindly ask you cite the paper as follows:

@inproceedings{hiremath2024hybrid,
  title = {Hybrid Top-Down Global Causal Discovery with Local Search for Linear and Nonlinear Additive Noise Models},
  author = {Hiremath, Sujai and Maasch, Jacqueline and Gao, Mengxiao and Ghosal, Promit and Gan, Kyra},
  booktitle = {The Thirty-eighth Annual Conference on Neural Information Processing Systems},
  year = {2024},
  url = {https://arxiv.org/pdf/2405.14496}
}