Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
VaRT: Variational Regression Trees
Sebastian Salazar
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 BART (50 trees) with VaRT for ATE estimation | VaRT · IHDP linear response surface | ATE estimate: 3.6 -> 3.86 | Improved |
| replace BART (50 trees) with VaRT for ATE estimation | VaRT · IHDP non-linear response surface | ATE estimate: 2.9 -> 3.80 | Improved |
| increase VaRT tree depth from 3 to 10 (ablation) | VaRT · concreteslump | RMSE: 0.009 -> 0.047 | Hurt |
| increase VaRT tree depth from 3 to 10 (ablation) | VaRT · autompg | RMSE: 0.116 -> 0.109 | Improved |
| increase VaRT tree depth from 3 to 10 (ablation) | VaRT · airfoil | RMSE: 0.151 -> 0.131 | Improved |
| increase VaRT tree depth from 3 to 10 (ablation) | VaRT · housing | RMSE: 0.101 -> 0.101 | No clear effect |
| single VaRT tree instead of 50-tree CatBoost ensemble | VaRT3 · concreteslump | RMSE: 0.209 -> 0.009 | Improved |
| single VaRT tree instead of 50-tree XGBoost ensemble | VaRT7 · airfoil | RMSE: 0.061 -> 0.131 | Hurt |
| single VaRT tree instead of 50-tree RandomForest | VaRT5 · housing | RMSE: 0.118 -> 0.097 | Improved |
| VaRT depth 5 versus CatBoost on a large dataset | VaRT · tamielectric (45781 datapoints) | RMSE: 0.503 -> 0.508 | No clear effect |
| VaRT depth 5 versus XGBoost on a large dataset | VaRT · kin40k (40000 datapoints) | RMSE: 0.110 -> 0.099 | Improved |
| VaRT (median) versus BART with 50 trees | VaRT · autos | RMSE: 0.075 -> 0.107 | Hurt |
Closest papers by meaning
- Predictive variational inference: Learn the predictively optimal posterior distribution (ICML 2026 · similarity 0.87)
- Advances in Variational Inference (TPAMI 2018 · similarity 0.86)
- Bayesian Additive Distribution Regression (NeurIPS 2026 · similarity 0.86)
- Symbolic Regression Enhanced Decision Trees for Classification Tasks (AAAI 2024 · similarity 0.86)
- Generative Model for Decision Trees (AAAI 2024 · similarity 0.85)
- Variational Polya Tree (NeurIPS 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.
