Research map / Optimization / Implicit bias and generalization
Stability and Generalization of Learning Algorithms that Converge to Global Optima
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 black-box stability analysis based on convergence to global minima and minimizer geometry | Learning algorithms for nonconvex losses satisfying PL or QG conditions · PL or QG loss functions | generalization stability | Helped |
| Apply the stability analysis to SGD, GD, RCD, and SVRG | SGD, GD, RCD, and SVRG · PL and strongly convex settings | generalization stability | Helped |
| Use SGD instead of GD | Simple neural networks with multiple local minima · Neural networks with multiple local minima | uniform stability | Helped |
Closest papers by meaning
- Fine-Grained Analysis of Stability and Generalization for Stochastic Gradient Descent (ICML 2020 · similarity 0.93)
- Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes (NeurIPS 2024 · similarity 0.91)
- Stability and Generalization Analysis of Decentralized SGD: Sharper Bounds Beyond Lipschitzness and Smoothness (ICML 2025 · similarity 0.90)
- Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters (NeurIPS 2026 · similarity 0.90)
- On the Unstable Convergence Regime of Gradient Descent (AAAI 2024 · similarity 0.90)
- Convergence Rates for Gradient Descent on the Edge of Stability for Overparametrised Least Squares (NeurIPS 2025 · similarity 0.90)
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.