Research map / Optimization / Nonconvex and smooth optimization
Global Optimality in Bivariate Gradient-based DAG Learning
Chang Deng, Kevin Bello, Pradeep Kumar Ravikumar, Bryon Aragam
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| decrease the penalty coefficient mu_k faster than the prescribed schedule (bad scheduling) (ablation) | homotopy gradient-flow path-following for bivariate DAG learning · 2-node linear SEM, population least squares | convergence to global minimum | Hurt |
| use the prescribed mu_k schedule (Line 3 of Algorithm 1) instead of a faster decrease (ablation) | homotopy gradient-flow path-following for bivariate DAG learning · 2-node linear SEM, population least squares | convergence to global minimum | Improved |
| vary the initialization of the gradient flow path under the proper schedule | homotopy gradient-flow path-following for bivariate DAG learning · 2-node linear SEM, population least squares | convergence to global minimum | No clear effect |
| replace gradient flow with gradient descent | homotopy path-following scheme · 2-node linear SEM, appendix experiments | convergence to global minimum | No clear effect |
Closest papers by meaning
- Analytic DAG Constraints for Differentiable DAG Learning (ICLR 2025 · similarity 0.88)
- On the Role of Sparsity and DAG Constraints for Learning Linear DAGs (NeurIPS 2020 · similarity 0.88)
- DAGs with NO TEARS: Continuous Optimization for Structure Learning (NeurIPS 2018 · similarity 0.87)
- Markov Equivalence and Consistency in Differentiable Structure Learning (NeurIPS 2024 · similarity 0.86)
- CoLiDE: Concomitant Linear DAG Estimation (ICLR 2024 · similarity 0.86)
- Learning Gaussian DAG Models without Condition Number Bounds (ICML 2025 · similarity 0.85)
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.
