Research map / Learning theory and algorithms / Kernels and regression theory
Learning Data-adaptive Non-parametric Kernels
Fanghui Liu, Xiaolin Huang, Chen Gong, Jie Yang, Li Li
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 |
|---|---|---|---|
| learn data-adaptive low-rank bounded matrix F on Gaussian kernel (DANK) vs SVM-CV | SVM with Gaussian kernel · UCI diabetic | test accuracy (%): 73.0 -> 81.2 | Improved |
| learn DANK matrix F | SVM with Gaussian kernel · UCI heart | test accuracy (%): 81.9 -> 87.9 | Improved |
| learn DANK matrix F | SVM with Gaussian kernel · UCI glass | test accuracy (%): 69.8 -> 74.5 | Improved |
| learn DANK matrix F | SVM with Gaussian kernel · UCI monks3 | test accuracy (%): 93.0 -> 93.0 | No clear effect |
| learn DANK matrix F | SVM with Gaussian kernel · UCI monks2, sonar, wine | test accuracy (%): 85.8 -> 86.7 | Mixed |
| add bounded constraint and low-rank structure on F (DANK vs unconstrained MKL-uniform) (ablation) | MKL-uniform · UCI diabetic | test accuracy (%): 61.9 -> 81.2 | Improved |
| add bounded and low-rank constraints on F (DANK vs MKL-uniform) (ablation) | MKL-uniform · UCI glass | test accuracy (%): 53.0 -> 74.5 | Improved |
| add bounded constraint and low-rank structure to KNPL (DANK) (ablation) | KNPL · UCI monks3 | test accuracy (%): 88.7 -> 93.0 | Improved |
| add bounded constraint and low-rank structure to KNPL (DANK) (ablation) | KNPL · UCI monks2 | test accuracy (%): 83.3 -> 86.7 | Improved |
| add bounded constraint and low-rank structure to KNPL (DANK) (ablation) | KNPL · UCI spect | test accuracy (%): 79.7 -> 78.9 | Hurt |
| use DANK instead of LogDet | LogDet · UCI monks1 | test accuracy (%): 86.6 -> 83.6 | Hurt |
| use DANK instead of LogDet | LogDet · UCI heart | test accuracy (%): 80.6 -> 87.9 | Improved |
Closest papers by meaning
- Adaptive kernel predictors from feature-learning infinite limits of neural networks (ICML 2025 · similarity 0.85)
- Scalable and adaptive prediction bands with kernel sum-of-squares (NeurIPS 2025 · similarity 0.85)
- Inverse M-Kernels for Linear Universal Approximators of Non-Negative Functions (NeurIPS 2024 · similarity 0.85)
- Kernel-based guarantees for nonlinear parametric models in Bayesian optimization (NeurIPS 2026 · similarity 0.84)
- On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity (NeurIPS 2024 · similarity 0.84)
- Joker: Joint Optimization Framework for Lightweight Kernel Machines (ICML 2025 · 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.
