Research map / Learning theory and algorithms / Kernels and regression theory
On Quantile Regression in Reproducing Kernel Hilbert Spaces with the Data Sparsity Constraint
Chong Zhang, Yufeng Liu, Yichao Wu
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 squared norm penalty with data sparsity constraint (GACV) | Quantile regression in RKHS · Simulation Example 1 (tau=0.1, homoscedastic normal, n=30) | prediction error: 0.760 -> 0.517 | Improved |
| replace squared norm penalty with data sparsity constraint (SIC) | Quantile regression in RKHS · Simulation Example 1 (tau=0.1, t3 noise, n=30) | prediction error: 1.013 -> 0.699 | Improved |
| replace squared norm penalty with data sparsity constraint (GACV) | Quantile regression in RKHS · real data caution (tau=0.1) | 100 x prediction error: 9.782 -> 8.433 | Improved |
| replace squared norm penalty with data sparsity constraint (GACV) | Quantile regression in RKHS · real data CobarOre (tau=0.1) | 100 x prediction error: 15.74 -> 12.19 | Improved |
| replace squared norm penalty with data sparsity constraint (GACV) | Quantile regression in RKHS · real data sniffer (tau=0.1) | 100 x prediction error: 6.372 -> 5.416 | Improved |
| replace squared norm penalty with data sparsity constraint (SIC) | Quantile regression in RKHS · real data cpus (tau=0.1) | 100 x prediction error: 4.575 -> 5.242 | Hurt |
| replace squared norm penalty with data sparsity constraint | Quantile regression in RKHS · 20 real data sets plus baseball | prediction error | Mixed |
| replace squared norm penalty with data sparsity constraint at large n | Quantile regression in RKHS · simulation Examples 1-3, large n | prediction error | No clear effect |
| replace squared norm penalty with data sparsity constraint on wiggly truth | Quantile regression in RKHS · simulation Example 3 (moderate n) | prediction error | No clear effect |
| penalize the intercept b or not (ablation) | Quantile regression in RKHS · simulation Examples 1-3 | prediction error | No clear effect |
| select tuning parameters with GACV instead of SIC (ablation) | Quantile regression in RKHS · simulation Examples 1-3 | prediction error: 0.910 -> 0.760 | Improved |
Closest papers by meaning
- Distributed Learning of Conditional Quantiles in the Reproducing Kernel Hilbert Space (NeurIPS 2022 · similarity 0.88)
- Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration (NeurIPS 2019 · similarity 0.87)
- Functional Linear Regression with Mixed Predictors (JMLR 2022 · similarity 0.87)
- Generalization Properties of hyper-RKHS and its Applications (JMLR 2021 · similarity 0.87)
- Distributed High-Dimensional Quantile Regression: Estimation Efficiency and Support Recovery (ICML 2024 · similarity 0.86)
- Optimal Kernel Quantile Learning with Random Features (ICML 2024 · 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.
