Research map / Learning theory and algorithms / Prediction and decision losses
Partitioning Structure Learning for Segmented Linear Regression Trees
Xiangyu Zheng, Song Xi Chen
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 |
|---|---|---|---|
| SLRT instead of CART | single tree · Simulated surface m(X) | RMSPE: 0.073 -> 0.047 | Improved |
| LASSO variable selection on leaf nodes (SLRT-LASSO vs SLRT-LS) | SLRT · Boston Housing | RMSPE: 0.174 -> 0.170 | Improved |
| LASSO variable selection on leaf nodes | SLRT · Auto-mobile | RMSPE: 0.154 -> 0.140 | Improved |
| LASSO variable selection on leaf nodes | SLRT · Pyrimidine | RMSPE: 0.088 -> 0.093 | Hurt |
| SLRT-LASSO instead of GUIDE | single tree · Kinematics | RMSPE: 0.140 -> 0.138 | Improved |
| SLRT-LASSO instead of GUIDE | single tree · Parkinson | RMSPE: 9.300 -> 9.327 | Hurt |
| SLRT-LASSO instead of MARS | single tree · Pyrimidine | RMSPE: 0.074 -> 0.093 | Hurt |
| SLRT as base predictor in random forest instead of CART | random forest · Auto-mpg | RMSPE: 3.273 -> 2.633 | Improved |
| SLRT as base predictor in random forest instead of CART | random forest · Kinematics | RMSPE: 0.249 -> 0.117 | Improved |
| SLRT as base predictor in random forest instead of CART | random forest · Pyrimidine | RMSPE: 0.073 -> 0.078 | Hurt |
| weighted RF instead of RF with SLRT base | ensemble · Boston Housing | RMSPE: 0.162 -> 0.158 | Improved |
| weighted RF instead of RF with SLRT base | ensemble · Computer Hardware | RMSPE: 38.49 -> 36.77 | Improved |
Closest papers by meaning
- Hierarchical Shrinkage: Improving the accuracy and interpretability of tree-based models. (ICML 2022 · similarity 0.86)
- Cross-Validated Variable Selection in Tree-Based Methods Improves Predictive Performance (TPAMI 2016 · similarity 0.86)
- Piecewise Constant and Linear Regression Trees: An Optimal Dynamic Programming Approach (ICML 2024 · similarity 0.86)
- Symbolic Regression Enhanced Decision Trees for Classification Tasks (AAAI 2024 · similarity 0.84)
- Partition Tree: Conditional Density Estimation over General Outcome Spaces (NeurIPS 2026 · similarity 0.84)
- Minimax Rates and Spectral Distillation for Tree Ensembles (NeurIPS 2026 · 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.
