Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Spatial Multivariate Trees for Big Data Bayesian Regression
Michele Peruzzi, David B. Dunson
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 full tree depth delta=M instead of delta=1 (ablation) | SpamTrees · Synthetic bivariate data | RMSE of y: 0.8027 -> 0.7171 | Improved |
| use full tree depth delta=M instead of delta=1 (ablation) | SpamTrees · Synthetic bivariate data | MAE of y: 0.5737 -> 0.5144 | Improved |
| use full tree depth delta=M instead of delta=1 (ablation) | SpamTrees · Synthetic data, covariance parameter estimation | RMSE of theta: 3.5883 -> 2.2882 | Improved |
| use SpamTrees delta=M instead of meshed GP | Q-MGP · Synthetic bivariate data | RMSE of y: 0.7529 -> 0.7171 | Improved |
| use SpamTrees delta=M instead of INLA | INLA · Synthetic bivariate data | RMSE of y: 0.7521 -> 0.7171 | Improved |
| use spatial DAG model instead of non-spatial BART | BART · Synthetic bivariate data | RMSE of y: 0.8820 -> 0.7171 | Improved |
| use SpamTrees delta=M instead of low-rank GP | lowrank · Synthetic bivariate data | RMSE of y: 1.0230 -> 0.7171 | Improved |
| use SpamTrees delta=M instead of independent partitioning | ind-part · Synthetic bivariate data | RMSE of y: 1.0796 -> 0.7171 | Improved |
| use SpamTrees delta=M instead of low-rank for MAE of theta-less outcome | lowrank · Synthetic data, covariance parameter estimation | MAE of theta: 1.4895 -> 1.6873 | Hurt |
| use SpamTrees delta=M instead of low-rank | lowrank · Synthetic data, covariance parameter estimation | RMSE of theta: 2.6953 -> 2.2882 | Improved |
| use SpamTrees instead of tessellated MGP | Q-MGP · MODIS-GHCN climate data | prediction error and coverage | Improved |
Closest papers by meaning
- Spatial meshing for general Bayesian multivariate models (JMLR 2024 · similarity 0.89)
- Consistent Bayesian Spatial Domain Partitioning Using Predictive Spanning Tree Methods (NeurIPS 2026 · similarity 0.86)
- Discovering Latent Causal Graphs from Spatiotemporal Data (ICML 2025 · similarity 0.85)
- Learning from Summarized Data: Gaussian Process Regression with Sample Quasi-Likelihood (AAAI 2025 · similarity 0.84)
- Bayesian Additive Distribution Regression (NeurIPS 2026 · similarity 0.84)
- Smooth Sailing: Lipschitz-Driven Uncertainty Quantification for Spatial Associations (NeurIPS 2025 · similarity 0.83)
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.
