Research map / Optimization / Implicit bias and generalization
Two-layer neural network on infinite dimensional data: global optimization guarantee in the mean-field regime
Naoki Nishikawa, Taiji Suzuki, Atsushi Nitanda, Denny Wu
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 |
|---|---|---|---|
| train mean-field two-layer network on functional data (PDA or P-SDCA) instead of linear/kernel estimators | mean-field two-layer neural network (PDA, P-SDCA) · synthetic non-linear functional regression | test loss | Improved |
| ridge regularization lambda among 0.1, 1, 10 | Ridge regression baseline · synthetic non-linear functional regression | test loss | Mixed |
| compare PDA with P-SDCA optimizers | mean-field neural network · synthetic non-linear functional regression | test loss vs gradient evaluations | No clear effect |
Closest papers by meaning
- Global Convergence of Three-layer Neural Networks in the Mean Field Regime (ICLR 2021 · similarity 0.90)
- Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective (ICML 2024 · similarity 0.89)
- Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure (ICLR 2025 · similarity 0.89)
- Asymptotics of feature learning in two-layer networks after one gradient-step (ICML 2024 · similarity 0.87)
- Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $\mu$ Parametrization (ICML 2025 · similarity 0.87)
- Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws (NeurIPS 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.
