Research map / Learning theory and algorithms / Kernels and regression theory
Joint quantile regression in vector-valued RKHSs
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| joint estimation (JQR) instead of independent quantile regressors | kernel quantile regression · 20 UCI/R datasets | pinball loss: better on 12 vs 8 datasets (5 vs 1 significant) | Helped |
| joint estimation (JQR) instead of MTFL | kernel quantile regression · 20 UCI/R datasets | pinball loss: 15 vs 5 datasets (11 vs 1 significant) | Helped |
| joint estimation (JQR) instead of independent / hard non-crossing | kernel quantile regression · 20 UCI/R datasets | crossing loss: 18 vs 1 favorable datasets (9 vs 0 significant) | Helped |
| joint estimation (JQR) instead of MTFL | kernel quantile regression · 20 UCI/R datasets | crossing loss: 16 vs 3 (12 vs 1 significant) | Helped |
| JQR instead of IND. | kernel quantile regression · mcycle | pinball loss x100: 89.2 -> 84.3 | Helped |
| JQR instead of IND. | kernel quantile regression · mcycle | crossing loss x100: 2.10 -> 0.14 | Helped |
| JQR instead of IND. | kernel quantile regression · engel | crossing loss x100: 1.50 -> 0.06 | Helped |
| JQR instead of IND. | kernel quantile regression · snowgeese | pinball loss x100: 68.4 -> 76.0 | Hurt |
| JQR instead of IND. | kernel quantile regression · engel | pinball loss x100: 61.3 -> 64.4 | Hurt |
| JQR instead of IND. | kernel quantile regression · highway | pinball loss x100: 102.9 -> 103.7 | Hurt |
| PDCD instead of off-the-shelf QP solver | joint quantile regression training · synthetic, n=2000 | CPU time (s): 3416.55 -> 958.93 | Helped |
| PDCD instead of QP solver | joint quantile regression training · synthetic, n=250 | CPU time (s): 8.73 -> 18.69 | Hurt |
Closest papers by meaning
- Transfer Learning Through Conditional Quantile Matching (NeurIPS 2026 · similarity 0.86)
- Optimal Kernel Quantile Learning with Random Features (ICML 2024 · similarity 0.84)
- Relaxed Quantile Regression: Prediction Intervals for Asymmetric Noise (ICML 2024 · similarity 0.84)
- Distributed High-Dimensional Quantile Regression: Estimation Efficiency and Support Recovery (ICML 2024 · similarity 0.84)
- Kernel Quantile Embeddings and Associated Probability Metrics (ICML 2025 · similarity 0.83)
- Kernel conditional tests from learning-theoretic bounds (NeurIPS 2025 · similarity 0.82)
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.