Research map / Learning theory and algorithms / Combinatorial and search optimization
Learning Bayesian Networks with Bounded Tree-width via Guided Search
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 |
|---|---|---|---|
| add guided I-score k-tree search before sampling BN (S2+ vs S2) | S2 · BDeu score, community | BDeu score: −9.330·104 -> −8.384·104 | Helped |
| S2+ vs S2 | S2 · BDeu score, hill | BDeu score: −1.137·103 -> −8.784·102 | Helped |
| learn BN from k-tree with S2 sampling instead of exact K&P (ablation) | guided k-tree search · BDeu score, community | BDeu score: −8.756·104 -> −8.384·104 | Helped |
| guided search vs MILP exact (time-limited) on mid-size data | MILP · BDeu score, audio | BDeu score: −2.541·103 -> −2.126·103 | Helped |
| S2+ vs exact MILP on small data | MILP · BDeu score, wdbc | BDeu score: −6.995·103 -> −7.143·103 | Hurt |
| bound tree-width at 4 vs unconstrained GOBNILP | S2+ · BDeu score, wdbc | BDeu score: −6.863·103 -> −7.143·103 | Hurt |
| learn bounded tree-width network for inference instead of original network | Rand60 · inference time | time ratio: 4.3% of original | Helped |
| S2+ sample-learn-infer vs LBP | approximate inference · UAI 2014 MAR average | Hellinger error: 0.0367 -> 0.0165 | Helped |
| S2+ vs SampleSearch on DBN networks | SampleSearch · UAI 2014 DBN | Hellinger error: 0.0422 -> 0.0572 | Hurt |
Closest papers by meaning
- Learning Treewidth-Bounded Bayesian Networks with Thousands of Variables (NeurIPS 2016 · similarity 0.94)
- Turbocharging Treewidth-Bounded Bayesian Network Structure Learning (AAAI 2021 · similarity 0.91)
- Learning Fast-Inference Bayesian Networks (NeurIPS 2021 · similarity 0.90)
- Learning Bayesian Networks in the Presence of Structural Side Information (AAAI 2022 · similarity 0.90)
- Learnability of Parameter-Bounded Bayes Nets (AAAI 2025 · similarity 0.86)
- Near-Optimal Decision Trees in a SPLIT Second (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.