Research map / Architectures and efficiency / RNNs and normalization
Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction
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 |
|---|---|---|---|
| add weight decay to GD on scale-invariant net (ablation) | VGG-11 with BN, full-batch GD · CIFAR-10 test | test accuracy (%): 66.4 -> 84.3 | Helped |
| add batch normalization (ablation) | VGG-11 with GD+WD · CIFAR-10 test | test accuracy (%): 56.8 -> 84.3 | Helped |
Closest papers by meaning
- Normalization Layers Are All That Sharpness-Aware Minimization Needs (NeurIPS 2023 · similarity 0.90)
- Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization (NeurIPS 2023 · similarity 0.90)
- The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks (NeurIPS 2019 · similarity 0.90)
- On the Nonlinearity of Layer Normalization (ICML 2024 · similarity 0.88)
- Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization (NeurIPS 2024 · similarity 0.87)
- Simplicity Bias via Global Convergence of Sharpness Minimization (ICML 2024 · 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.