Research map / Learning theory and algorithms / Kernels and regression theory
Kernel-based L_2-Boosting with Structure Constraints
Yao Wang, Xin Guo, Shao-Bo Lin
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 KReBooT instead of KRTboosting | kernel boosting · Simulation, m=1000, SNR 7.1 | test MSE: 0.034 -> 0.030 | Improved |
| use KReBooT instead of epsilon-Kboosting | kernel boosting · Simulation, m=10000, SNR 7.1 | test MSE: 0.018 -> 0.014 | Improved |
| use KReBooT instead of KRRN | kernel regression · Simulation, m=500, SNR 3.6 | test MSE: 0.127 -> 0.088 | Improved |
| use GBDT instead of KReBooT | KReBooT · Simulation, m=1000, SNR 7.1 | test MSE: 0.030 -> 0.026 | Hurt |
| use KReBooT instead of KRboosting | kernel boosting · Simulation, m=1000, SNR 7.1 | test MSE: 0.029 -> 0.030 | No clear effect |
| use KReBooT instead of Klasso | kernel regression · Simulation, m=1000, SNR 3.6 | test MSE: 0.042 -> 0.043 | No clear effect |
| use KReBooT instead of epsilon-Kboosting | kernel boosting · Concrete Compressive Strength (real data) | RMSE: 5.86 -> 5.27 | Improved |
| use KReBooT instead of KRRN | kernel regression · Diabetes (real data) | RMSE: 58.99 -> 56.66 | Improved |
| use KReBooT instead of KRTboosting | kernel boosting · Abalone (real data) | RMSE: 2.35 -> 2.21 | Improved |
| use GBDT instead of KReBooT | KReBooT · Concrete Compressive Strength (real data) | RMSE: 5.27 -> 5.23 | Hurt |
| add re-scaling and truncation (KReBooT) over KRboosting in overfitting test (ablation) | KRboosting · Simulation, m=1000, SNR 7.1 | test MSE vs iterations | Improved |
| choose c0 in [0.1, 5] for step size (ablation) | KReBooT · Simulation, m=1000, SNR 7.1 and 3.6 | test MSE vs iterations | Improved |
Closest papers by meaning
- Boosted Kernel Ridge Regression: Optimal Learning Rates and Early Stopping (JMLR 2019 · similarity 0.88)
- Sparse Kernel Regression with Coefficient-based $\ell_q-$regularization (JMLR 2019 · similarity 0.87)
- Statistical Inference for Gradient Boosting Regression (NeurIPS 2025 · similarity 0.84)
- Joker: Joint Optimization Framework for Lightweight Kernel Machines (ICML 2025 · similarity 0.84)
- Supervised Kernel Thinning (NeurIPS 2024 · similarity 0.84)
- On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity (NeurIPS 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.
