Research map / Optimization / Implicit bias and generalization
Neural Tangent Kernel: Convergence and Generalization in Neural Networks
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 hidden width from 500 to 10000 | depth-4 ReLU MLP · unit-circle regression f*(x)=x1x2 | NTK variance and drift during training | Helped |
| increase hidden width from 50 to 1000 | depth-4 ReLU MLP · least-squares on 4 unit-circle points | match to limiting Gaussian distribution | No clear effect |
| use bias factor beta 1.0 instead of 0.1 | ReLU MLP NTK · MNIST | gap between first and second NTK principal components (trainability) | Hurt |
Closest papers by meaning
- On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory (NeurIPS 2024 · similarity 0.93)
- Gradient Descent in Neural Networks as Sequential Learning in Reproducing Kernel Banach Space (ICML 2023 · similarity 0.92)
- Neural Tangent Kernels Under Stochastic Data Augmentation (AAAI 2026 · similarity 0.91)
- Optimized Random Features for the Neural Tangent Kernel (Student Abstract) (AAAI 2025 · similarity 0.90)
- Divergence of Neural Tangent Kernel in Classification Problems (ICLR 2025 · similarity 0.90)
- Neural Tangent Kernels Motivate Cross-Covariance Graphs in Neural Networks (ICML 2024 · similarity 0.89)
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.