Research map / Learning theory and algorithms / Kernels and regression theory
Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime
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 |
|---|---|---|---|
| increase sample size n past the noise crossover | KRR with lambda=0 · Gaussian design, weak regularization | excess error decay exponent: 2*alpha*min(r,1) -> 0 | Mixed |
| optimally regularize instead of using fixed small regularization at large n | KRR · Gaussian design, n >> n2* | excess error decay exponent: 2*alpha*min(r,1) -> 2*alpha*min(r,1)/(1+2*alpha*min(r,1)) | Mixed |
| add label noise | KRR with lambda=0 · Fashion MNIST polynomial kernel, sigma=0.5 and 1 | learning curve slope | Mixed |
| optimize regularization per sample size | KRR · Fashion MNIST | excess error | No clear effect |
| optimize regularization per sample size | KRR · MNIST, noise sigma=0.5 and 1 | excess error | Mixed |
Closest papers by meaning
- A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression (NeurIPS 2024 · similarity 0.92)
- Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality (NeurIPS 2024 · similarity 0.91)
- Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning (NeurIPS 2025 · similarity 0.91)
- Generalization error of spectral algorithms (ICLR 2024 · similarity 0.91)
- Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum (ICML 2024 · similarity 0.90)
- Generalization in Kernel Regression Under Realistic Assumptions (ICML 2024 · similarity 0.90)
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.