Research map / Learning theory and algorithms / Kernels and regression theory
On the Saturation Effect of Kernel Ridge Regression
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 |
|---|---|---|---|
| Increasing smoothness alpha beyond 2 with KRR (saturation): rate stops improving and declines | KRR · Toy 1D Sobolev H^1, f*=e_2 | convergence rate: 0.80 at alpha=2 to 0.54 at alpha=3.5 | Hurt |
| Gradient flow with early stopping used instead of KRR (spectral algorithm with high qualification) | spectral regularization (gradient flow) · Toy 1D Sobolev H^1, f*=e_2 | convergence rate: 0.85 vs 0.54 at alpha=3.5 | Helped |
Closest papers by meaning
- On the Saturation Effects of Spectral Algorithms in Large Dimensions (NeurIPS 2024 · similarity 0.90)
- Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning (NeurIPS 2025 · similarity 0.88)
- A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression (NeurIPS 2024 · similarity 0.88)
- Kernel conditional tests from learning-theoretic bounds (NeurIPS 2025 · similarity 0.86)
- Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality (NeurIPS 2024 · similarity 0.86)
- Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum (ICML 2024 · similarity 0.86)
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.