Research map / Graph learning / Graph algorithms and clustering
DAGs with NO TEARS: Continuous Optimization for Structure Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use NOTEARS instead of FGS | Protein signaling network structure learning · Protein signaling network | SHD: 22 vs. 22 | No clear effect |
| Add ℓ1 regularization (ablation) | NOTEARS · Small-sample structure learning (n=20) | structure recovery | Helped |
| Add ℓ1 regularization (ablation) | NOTEARS · Structure learning across graph types | structure recovery | Helped |
| Use a fixed threshold ω=0.3 rather than the setting-specific optimal threshold (ablation) | NOTEARS · Simulated graph structure recovery | structure recovery | No clear effect |
| Reduce the edge-weight scale α (ablation) | NOTEARS · ER-2, d=20, n=1000 | SHD | Hurt |
| Use global continuous optimization rather than greedy local edge search | NOTEARS vs. FGS · Simulated structure learning, especially SF-4 | SHD | Helped |
| Use NOTEARS rather than the exact global minimizer | NOTEARS vs. GOBNILP · ER2, n=1000, λ=0 | F(W): 4.97 -> 5.02 | Hurt |
Closest papers by meaning
- DAGs with No Curl: An Efficient DAG Structure Learning Approach (ICML 2021 · similarity 0.94)
- Markov Equivalence and Consistency in Differentiable Structure Learning (NeurIPS 2024 · similarity 0.91)
- ProDAG: Projected Variational Inference for Directed Acyclic Graphs (NeurIPS 2025 · similarity 0.90)
- Constraint-Free Structure Learning with Smooth Acyclic Orientations (ICLR 2024 · similarity 0.90)
- Analytic DAG Constraints for Differentiable DAG Learning (ICLR 2025 · similarity 0.88)
- CoLiDE: Concomitant Linear DAG Estimation (ICLR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.