Research map / Learning theory and algorithms / Kernels and regression theory
On the Random Conjugate Kernel and Neural Tangent Kernel
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 network depth d (feedforward, width n scaled so c=1, β≈1) | feedforward ReLU network CK and NTK diagonal · KS test vs log-normal limit | KS p-value: p=1.6e-10 at depth 2 to 0.713 at depth 15 | Helped |
| increase number of residual branches m (with sum of c_i kept fixed) | residual network CK diagonal · KS test vs log-normal limit | KS p-value: p=0.00E+00 at 1 branch to 1.36E-01 at 100 branches | Helped |
| theoretical moment prediction for feedforward CK | 3-layer feedforward network · n=100, 1000 samples | first moment E[Σ]: predicted 2.50E-1 vs estimated 2.52E-01 | No clear effect |
Closest papers by meaning
- Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks (NeurIPS 2020 · similarity 0.91)
- Finite Depth and Width Corrections to the Neural Tangent Kernel (ICLR 2020 · similarity 0.89)
- Convergence of Near-Linear Width ReLU Networks with Unbalanced Initialization (NeurIPS 2026 · similarity 0.88)
- On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory (NeurIPS 2024 · similarity 0.87)
- Eigen Analysis of Conjugate Kernel and Neural Tangent Kernel (ICML 2025 · similarity 0.87)
- Optimized Random Features for the Neural Tangent Kernel (Student Abstract) (AAAI 2025 · 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.