Research map / Learning theory and algorithms / Kernels and regression theory
Infinite Kernel Learning: Generalization Bounds and Algorithms
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 |
|---|---|---|---|
| learn kernel over continuously parameterized infinite kernel set (IFKL) instead of finite prescribed set (FKL) (ablation) | PEP-based kernel learning · sonar | test accuracy: 82.53±5.35 -> 84.90±6.08 | Helped |
| IFKL vs FKL on most datasets (ablation) | PEP-based kernel learning · 10 LIBSVM datasets | test accuracy: 85.85±0.84 -> 85.87±0.88 | No clear effect |
| PEP-based infinite kernel learning vs prior infinite kernel learning (IKL) | kernel learning · 10 LIBSVM datasets | test accuracy: 84.90±6.08 vs 83.04±6.50 (sonar) | Helped |
| PEP-based finite kernel learning vs SimpleMKL | kernel learning · liver-disorders | test accuracy: 66.92±6.64 -> 70.52±5.95 | Helped |
| infinite kernel methods vs finite kernel MKL methods | kernel learning · 10 LIBSVM datasets | test accuracy: 93.67±1.07 vs 91.53±1.26 (ionosphere) | Helped |
| IFKL vs SimpleMKL on svmguide3 | kernel learning · svmguide3 | test accuracy: 82.81±0.71 -> 82.96±0.71 | No clear effect |
Closest papers by meaning
- Generalization in Kernel Regression Under Realistic Assumptions (ICML 2024 · similarity 0.90)
- Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel (NeurIPS 2025 · similarity 0.89)
- The optimality of kernel classifiers in Sobolev space (ICLR 2024 · similarity 0.88)
- On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity (NeurIPS 2024 · similarity 0.87)
- Generalization error of spectral algorithms (ICLR 2024 · similarity 0.87)
- On Statistical Learning Theory for Distributional Inputs (ICML 2024 · similarity 0.87)
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.