Research map / Learning theory and algorithms / Kernels and regression theory
Precise Learning Curves and Higher-Order Scalings for Dot-product Kernel Regression
Lechao Xiao, Hong Hu, Theodor Misiakiewicz, Yue Lu, Jeffrey Pennington
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 |
|---|---|---|---|
| Increase the spectral gap Gap between consecutive kernel eigenvalue levels (2, 8, 32, 128) (ablation) | Dot-product kernel ridgeless regression · Synthetic sphere data, d=24 | test error learning curve | Mixed |
| Use a small spectral gap (Gap=8 or 2) (ablation) | Dot-product kernel ridgeless regression · Synthetic sphere data | learning curve monotonicity | Improved |
| Increase input dimension d toward infinity (ablation) | Theoretical learning-curve prediction · Second peak r=2, 32 runs | gap between simulation and prediction | Improved |
| Replace dot-product kernel with one-hidden-layer CNN kernel | Learning-curve theory · d0=20, p=6 | agreement of prediction with simulation | No clear effect |
Closest papers by meaning
- Learning Curves of Stochastic Gradient Descent in Kernel Regression (ICML 2025 · similarity 0.89)
- 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 0.87)
- Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning (NeurIPS 2025 · similarity 0.87)
- No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions (ICML 2025 · similarity 0.87)
- Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality (NeurIPS 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.
