Research map / Optimization / Implicit bias and generalization
Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the 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 |
|---|---|---|---|
| Use early stopping with T=n^α, α∈(0,1) | Gradient Descent on shallow neural networks with label noise · Well-specified regression with label noise | statistical risk | Helped |
| Control risk using the closest-to-initialization empirical-risk minimizer rather than relaxing to the NTK solution | Gradient Descent on shallow neural networks · Regression without label noise | statistical risk bound | Helped |
| Increase network width to satisfy m≳(ηT)^5 | Gradient Descent on shallow neural networks · Generalisation and risk bounds | generalisation gap | Helped |
Closest papers by meaning
- Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks (NeurIPS 2022 · similarity 0.94)
- Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods (ICLR 2025 · similarity 0.89)
- Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel (NeurIPS 2025 · similarity 0.89)
- Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Power (ICLR 2025 · similarity 0.88)
- On the Unstable Convergence Regime of Gradient Descent (AAAI 2024 · similarity 0.88)
- Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes (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.