Research map / Probabilistic and scientific modeling / Variational and generative sampling
Learning Ensembles of Cutset Networks
Tahrima Rahman, Vibhav Gogate
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 |
|---|---|---|---|
| use kernel-smoothed weight update (GBDE) instead of BDE (ablation) | boosted CutSet networks · 20 datasets average LL, fixed-depth CNet | average test LL: -55.15 -> -54.87 | Improved |
| use sequential EM instead of BDE for boosting (ablation) | boosted CutSet networks · 20 datasets average LL, fixed-depth CNet | average test LL: -55.15 -> -54.49 | Improved |
| use MCNet base models instead of CNet in boosting (SEQEM, fixed depth) (ablation) | SEQEM boosting · 20 datasets average LL | average test LL: -54.49 -> -53.23 | Improved |
| randomize OR-tree depth (variable depth) in bagging CNets (ablation) | bagged CNets · 20 datasets average LL | average test LL: -54.41 -> -53.86 | Improved |
| randomize OR-tree depth (variable depth) in bagging MCNets (ablation) | bagged MCNets · 20 datasets average LL | average test LL: -54.08 -> -53.10 | Improved |
| randomize depth (variable depth) in boosting CNets with SEQEM (ablation) | SEQEM boosting · 20 datasets average LL | average test LL: -54.49 -> -54.37 | No clear effect |
| replace EM-trained mixture (MCNet) with ECNet bagging/boosting | cutset network ensembles · 20 datasets average LL | average test LL: -54.50 -> -53.06 | Improved |
| ECNets vs ID-SPN | ECNet · 20 datasets average LL | average test LL: -53.89 -> -53.06 | Improved |
| use boosting rather than bagging | ECNet · 20 datasets average LL (Table 4) | average test LL: -53.06 -> -53.16 | No clear effect |
Closest papers by meaning
- Look Ma, No Latent Variables: Accurate Cutset Networks via Compilation (ICML 2019 · similarity 0.88)
- On Computing Optimal Tree Ensembles (ICML 2023 · similarity 0.87)
- Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again (NeurIPS 2026 · similarity 0.84)
- Free Lunch in the Forest: Functionally-Identical Pruning of Boosted Tree Ensembles (AAAI 2025 · similarity 0.84)
- Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs (ICLR 2024 · similarity 0.84)
- Distribution Learning Meets Graph Structure Sampling (NeurIPS 2025 · similarity 0.84)
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.
