Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Incorporating Grouping Information into Bayesian Decision Tree Ensembles
Junliang Du, Antonio Linero
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 |
|---|---|---|---|
| add correct grouping structure to BART prior (OG-BART vs SBART) | SBART · Simulation 4.1, Pg=5 | F1 and RMSE | Improved |
| use incorrectly specified grouping structure in OG-BART (ablation) | OG-BART · Simulation 4.1 | F1, RMSE | No clear effect |
| increase prior mean of alpha and psi from 1 to 10 with correct groups (ablation) | OG-BART · Simulation 4.1, Pg=50 | false positives | Hurt |
| add correct grouping structure to BART prior | SBART · Simulation 4.2 overlapping groups | F1, FN, RMSE | Improved |
| use incorrect overlapping grouping (ablation) | OG-BART · Simulation 4.2 | F1, FN, RMSE | No clear effect |
| replace OG-BART with overlapping group lasso | OG-BART · Simulation 4.2 | all metrics | Hurt |
| larger E(alpha), E(psi) prior means (ablation) | OG-BART · Simulation 4.2 | false positive rate | Hurt |
| replace SBART with OG-BART | SBART · Breast cancer gene expression | heldout deviance: 646 -> 620 | Improved |
| replace OG-Lasso with OG-BART | OG-Lasso · Breast cancer gene expression | heldout deviance: 797 -> 620 | Improved |
| replace cMCP with OG-BART | cMCP · Breast cancer gene expression | heldout deviance: 698 -> 620 | Improved |
| use larger prior means alpha, psi ~ Exp(10) (ablation) | OG-BART · Breast cancer gene expression | predictive performance | Mixed |
Closest papers by meaning
- The Non-Overlapping Statistical Approximation to Overlapping Group Lasso (JMLR 2024 · similarity 0.88)
- Global-Local Dirichlet Processes for Clustering Grouped Data in the Presence of Group-Specific Idiosyncratic Variables (ICML 2025 · similarity 0.86)
- Bayesian Additive Distribution Regression (NeurIPS 2026 · similarity 0.86)
- Very Fast Bayesian Additive Regression Trees on GPU (NeurIPS 2026 · similarity 0.85)
- A Unified Framework for Variable Selection in Model-Based Clustering with Missing Not at Random (NeurIPS 2025 · similarity 0.84)
- Multi-group Learning for Hierarchical Groups (ICML 2024 · 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.
