Research map / Learning theory and algorithms / Matrix and tensor methods
Truncated Matrix Power Iteration for Differentiable DAG Learning
Zhen Zhang, Ignavier Ng, Dong Gong, Yuhang Liu, Ehsan M Abbasnejad, Mingming Gong, Kun Zhang, Javen Qinfeng Shi
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 |
|---|---|---|---|
| replace Binomial DAG constraint with TMPI | DAG-GNN · 50-node ER1 nonlinear | SHD: 25.2 -> 22.2 | Improved |
| replace DAG constraint with TMPI | NOTEARS-MLP · 50-node ER1 MLP SEM | SHD: 16.9 -> 14.9 | Improved |
| replace DAG constraint with TMPI | DAG-GNN · Sachs | SHD: 16 -> 16 | No clear effect |
| replace DAG constraint with TMPI | DAG-GNN · Sachs | SHDC: 21 -> 17 | Improved |
| replace DAG constraint with TMPI | Gran-DAG · Sachs | SHD: 13 -> 12 | Improved |
| replace DAG constraint with TMPI | Gran-DAG · Sachs | SHDC: 11 -> 9 | Improved |
| replace DAG constraint with TMPI | Gran-DAG++ · Sachs | SHD: 13 -> 12 | Improved |
| replace DAG constraint with TMPI | Gran-DAG++ · Sachs | SHDC: 10 -> 9 | Improved |
| replace Exponential constraint with TMPI | GOLEM · 500-node ER2 Gaussian | SHD: 45.20 -> 14.45 | Improved |
| replace Binomial constraint with TMPI | GOLEM · 500-node ER2 Gaussian | SHD: 46.75 -> 14.45 | Improved |
| replace Exponential constraint with TMPI | GOLEM · 500-node ER2 Gaussian | running time (s): 882.22 -> 670.26 | Improved |
| replace Binomial constraint with TMPI | GOLEM · 500-node ER2 Gaussian | running time (s): 795.24 -> 670.26 | Improved |
Closest papers by meaning
- Analytic DAG Constraints for Differentiable DAG Learning (ICLR 2025 · similarity 0.92)
- Constraint-Free Structure Learning with Smooth Acyclic Orientations (ICLR 2024 · similarity 0.88)
- ProDAG: Projected Variational Inference for Directed Acyclic Graphs (NeurIPS 2025 · similarity 0.88)
- Markov Equivalence and Consistency in Differentiable Structure Learning (NeurIPS 2024 · similarity 0.87)
- CoLiDE: Concomitant Linear DAG Estimation (ICLR 2024 · similarity 0.87)
- Boosting Causal Structure Learning: An Asymmetric Exponential Modulation Gaussian-Based Adaptive Sample Reweighting Framework (AAAI 2025 · similarity 0.87)
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.
