Causal Discovery & Structure Learning Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

This list traces how causal discovery moved from combinatorial search to continuous optimization. It starts with the NOTEARS formulation and its neural extensions, then covers interventional, Bayesian, and survey perspectives that together give a practical map of the field.

Causal Discovery & Structure Learning: 10 key papers

1. DAGs with NO TEARS: Continuous Optimization for Structure Learning
   Zheng et al. arXiv 2018.
2. Learning Sparse Nonparametric DAGs
   Zheng et al. arXiv 2019.
3. Gradient-Based Neural DAG Learning
   Lachapelle et al. arXiv 2019.
4. DAG-GNN: DAG Structure Learning with Graph Neural Networks
   Yu et al. arXiv 2019.
5. Differentiable Causal Discovery from Interventional Data
   Brouillard et al. arXiv 2020.
6. Masked Gradient-Based Causal Structure Learning
   Ng et al. arXiv 2019.
7. Causal Discovery with Reinforcement Learning
   Zhu et al. arXiv 2019.
8. Amortized Inference for Causal Structure Learning
   Lorch et al. arXiv 2022.
9. Review of Causal Discovery Methods Based on Graphical Models
   Glymour et al. Frontiers in Genetics 2019.
10. D'ya like DAGs? A Survey on Structure Learning and Causal Discovery
    Vowels et al. arXiv 2021.

Related reading lists

• Causal Inference & RL
• Block MDPs & Latent State Discovery
• Low-Rank Structure in Machine Learning
• Bayesian Optimization & Global Optimization
• Graph Neural Networks & Message Passing
• Classical Planning & Search Algorithms
• Gaussian Processes
• Hyperparameter Optimization & AutoML