Research map / Optimization / Implicit bias and generalization
On Linear Stability of SGD and Input-Smoothness of Neural Networks
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 SGD with a bigger learning rate | Neural networks trained on FashionMNIST and CIFAR10 · FashionMNIST and CIFAR10 | parameter-gradient and input-gradient norms | Helped |
| Use a smaller batch size | Neural networks trained on FashionMNIST and CIFAR10 · FashionMNIST and CIFAR10 | parameter-gradient and input-gradient norms | Helped |
| Measure higher-order gradient norms (k=2 and k=3) | Neural networks trained on FashionMNIST, CIFAR10, and CIFAR100 · FashionMNIST, CIFAR10, and CIFAR100 | correlation between parameter-gradient and input-gradient norms | No clear effect |
Closest papers by meaning
- A Precise Characterization of SGD Stability Using Loss Surface Geometry (ICLR 2024 · similarity 0.91)
- A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity Bias (NeurIPS 2025 · similarity 0.90)
- Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon (NeurIPS 2025 · similarity 0.90)
- On the Unstable Convergence Regime of Gradient Descent (AAAI 2024 · similarity 0.89)
- Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters (NeurIPS 2026 · similarity 0.89)
- Convergence Rates for Gradient Descent on the Edge of Stability for Overparametrised Least Squares (NeurIPS 2025 · 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.