Research map / Learning theory and algorithms / Kernels and regression theory
Characterizing the spectrum of the NTK via a power series expansion
Michael Murray, Hui Jin, Benjamin Bowman, Guido Montufar
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 data with a low-effective-rank Gram matrix | Centered NTK · Arbitrary unit-sphere data | effective rank | Improved |
| Increase network depth | Feedforward NTK · Caltech101 and isotropic Gaussian data | dominant outlier prominence | Mixed |
| Approximate the NTK using the first 50 power-series coefficients | ReLU NTK · Input correlations with |ρ|<0.5 | absolute approximation error: 50 coefficients | Improved |
Closest papers by meaning
- Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks (JMLR 2024 · similarity 0.89)
- The asymptotic spectrum of the Hessian of DNN throughout training (ICLR 2020 · similarity 0.88)
- Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization (ICML 2022 · similarity 0.88)
- The Surprising Effectiveness of Infinite-Width NTKs for Characterizing and Improving Model Training (AAAI 2025 · similarity 0.88)
- On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory (NeurIPS 2024 · similarity 0.86)
- Neural Tangent Kernels Motivate Cross-Covariance Graphs in Neural Networks (ICML 2024 · 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.
