Research map / Learning theory and algorithms / Kernels and regression theory
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
Moritz Haas, David Holzmüller, Ulrike von Luxburg, Ingo Steinwart
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 |
|---|---|---|---|
| replace Laplace kernel with spiky-smooth kernel in ridgeless kernel regression | ridgeless kernel regression · synthetic 2D sphere data, 15 points | generalization | Improved |
| add omega_NTK high-frequency oscillation to ReLU activation (bandwidth 1/5000) | 2-layer wide neural network · synthetic 2D sphere data, 15 points | generalization under interpolation | Improved |
| use other choices of amplitude and frequency for the oscillation (ablation) | spiky-smooth activation · synthetic 2D sphere data | generalization | Hurt |
Closest papers by meaning
- Rethinking Benign Overfitting in Two-Layer Neural Networks (ICML 2025 · similarity 0.91)
- Benign Overfitting in Adversarial Training of Neural Networks (ICML 2024 · similarity 0.91)
- Generalization in Kernel Regression Under Realistic Assumptions (ICML 2024 · similarity 0.90)
- Noisy Interpolation Learning with Shallow Univariate ReLU Networks (ICLR 2024 · similarity 0.90)
- Transfer Learning for Benign Overfitting in High-Dimensional Linear Regression (NeurIPS 2025 · similarity 0.88)
- Benign overfitting in leaky ReLU networks with moderate input dimension (NeurIPS 2024 · similarity 0.88)
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.
