Research map / Optimization / Implicit bias and generalization
Control Batch Size and Learning Rate to Generalize Well: Theoretical and Empirical Evidence
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 ratio of batch size to learning rate | ResNet-110, VGG-19 (plain SGD) · CIFAR-10/100 | test accuracy: SCC −0.94 to −0.98 | Hurt |
| increase batch size at fixed learning rate | ResNet-110, VGG-19 · CIFAR-10/100 | test accuracy | Hurt |
| increase learning rate at fixed batch size | ResNet-110, VGG-19 · CIFAR-10/100 | test accuracy | Helped |
| increase learning rate at small batch size (16, 32) | VGG-19 · CIFAR-100 | test accuracy: SCC −0.80 (BS 16), −0.14 (BS 32) | Mixed |
Closest papers by meaning
- On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima (ICLR 2017 · similarity 0.91)
- On the Generalization Benefit of Noise in Stochastic Gradient Descent (ICML 2020 · similarity 0.91)
- Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks (NeurIPS 2025 · similarity 0.87)
- Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification (NeurIPS 2025 · similarity 0.87)
- Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization (NeurIPS 2024 · similarity 0.87)
- Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study (NeurIPS 2025 · similarity 0.87)
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.