Research map / Learning theory and algorithms / Kernels and regression theory
Data-Dependence of Plateau Phenomenon in Learning with Neural Network --- Statistical Mechanical Analysis
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 |
|---|---|---|---|
| decrease input scale mu1 (mean eigenvalue of input covariance) | two-layer soft-committee student-teacher network · theoretical order-parameter dynamics, Sigma = sigma I | plateau length | Hurt |
| decrease input scale mu1 | two-layer soft-committee student-teacher network · theoretical order-parameter dynamics, Sigma = sigma I | plateau height | Helped |
| increase spread of covariance eigenvalues (larger mu2) at fixed mu1=1 | two-layer soft-committee student-teacher network · two-eigenvalue covariance, theoretical dynamics | plateau length | Helped |
Closest papers by meaning
- Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra (ICLR 2025 · similarity 0.87)
- A Dynamical Model of Neural Scaling Laws (ICML 2024 · similarity 0.85)
- Scaling Laws in Linear Regression: Compute, Parameters, and Data (NeurIPS 2024 · similarity 0.84)
- Super Consistency of Neural Network Landscapes and Learning Rate Transfer (NeurIPS 2024 · similarity 0.84)
- On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling (NeurIPS 2025 · similarity 0.84)
- The Importance of Being Lazy: Scaling Limits of Continual Learning (ICML 2025 · similarity 0.84)
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.