Research map / Learning theory and algorithms / Kernels and regression theory
Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS
Lin Chen, Sheng Xu
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 |
|---|---|---|---|
| Use a smaller exponential-power exponent γ | Exponential power kernel on the sphere · S^(d-1) | RKHS inclusion | Improved |
| Use a smaller rational exponential-power exponent γ | Exponential power kernel on R^d · R^d | RKHS inclusion | Improved |
| Increase the number of ReLU NTK layers | ReLU NTK restricted to the sphere · S^(d-1) | RKHS function set | No clear effect |
Closest papers by meaning
- On the Similarity between the Laplace and Neural Tangent Kernels (NeurIPS 2020 · similarity 0.92)
- Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks (JMLR 2024 · similarity 0.87)
- Gradient Descent in Neural Networks as Sequential Learning in Reproducing Kernel Banach Space (ICML 2023 · similarity 0.87)
- Optimal Convergence Rates for Neural Operators (JMLR 2026 · similarity 0.86)
- Neural Tangent Kernel: Convergence and Generalization in Neural Networks (NeurIPS 2018 · similarity 0.86)
- Optimized Random Features for the Neural Tangent Kernel (Student Abstract) (AAAI 2025 · similarity 0.85)
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.
