Research map / Optimization / Implicit bias and generalization
Data-Dependent Stability of Stochastic Gradient Descent
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 the data-dependent stability bound instead of the uniform stability bound | SGD on MNIST with a three-layer convolutional network · MNIST | generalization-bound tightness | Helped |
| initialize SGD from a pre-trained position | SGD on MNIST with a three-layer convolutional network · MNIST | data-dependent generalization-bound tightness | Helped |
Closest papers by meaning
- Fine-Grained Analysis of Stability and Generalization for Stochastic Gradient Descent (ICML 2020 · similarity 0.95)
- Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm (ICML 2024 · similarity 0.92)
- Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent (AAAI 2025 · similarity 0.92)
- Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters (NeurIPS 2026 · similarity 0.91)
- Generalization Analysis of Biased Stochastic Gradient Methods for Minimax Problems (NeurIPS 2026 · similarity 0.91)
- Stochastic Optimization Schemes for Performative Prediction with Nonconvex Loss (NeurIPS 2024 · similarity 0.91)
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.