Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Learning Treewidth-Bounded Bayesian Networks with Thousands of Variables
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 k-G (greedy parent-set selection over orders) instead of S2 for structure learning under treewidth bound | treewidth-bounded BN structure learning · very large data sets (400-10000 variables) | wins out of 42 experiments | Helped |
| Use k-A* instead of S2 for structure learning under treewidth bound | treewidth-bounded BN structure learning · small data sets (k=4) | BIC score | Helped |
| Use k-A* or S2+ on very large data sets | k-A* and S2+ · very large data sets (400-10000 variables) | solutions found within time limit | Hurt |
| Exploring more orders with greedy k-G rather than optimal per-order k-A* (ablation) | k-G vs k-A* · large data sets (100-400 variables) | wins in pairwise comparisons | Helped |
| Bounded treewidth k=2 vs learning inverted trees (limitation) | k-A* and k-G · inverted tree synthetic data | W-score | No clear effect |
Closest papers by meaning
- Learning Bayesian Networks with Bounded Tree-width via Guided Search (AAAI 2016 · similarity 0.94)
- Turbocharging Treewidth-Bounded Bayesian Network Structure Learning (AAAI 2021 · similarity 0.93)
- Learning Bayesian Networks in the Presence of Structural Side Information (AAAI 2022 · similarity 0.90)
- Distribution Learning Meets Graph Structure Sampling (NeurIPS 2025 · similarity 0.87)
- Learnability of Parameter-Bounded Bayes Nets (AAAI 2025 · similarity 0.86)
- TreeVI: Reparameterizable Tree-structured Variational Inference for Instance-level Correlation Capturing (NeurIPS 2024 · 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.