Research map / Optimization / Implicit bias and generalization
On the generalization of learning algorithms that do not converge
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 CIFAR10 label-corruption probability | ResNet18 trained with SGD · CIFAR10 | test error | Hurt |
| Increase CIFAR10 label-corruption probability | ResNet18 trained with SGD · CIFAR10 | generalization gap | Mixed |
| Increase CIFAR10 label-corruption probability | VGG16 trained with SGD · CIFAR10 | estimated lower bound on SAS coefficient | Hurt |
| Use test-loss autocorrelation magnitude as a predictor | ResNet18 trained with SGD · CIFAR10 with corrupted labels | generalization-gap prediction | Helped |
Closest papers by meaning
- Train faster, generalize better: Stability of stochastic gradient descent (ICML 2016 · similarity 0.93)
- Stability and Generalization of Learning Algorithms that Converge to Global Optima (ICML 2018 · similarity 0.93)
- Generalization at the Edge of Stability (NeurIPS 2026 · similarity 0.90)
- Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness (NeurIPS 2024 · similarity 0.89)
- A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity Bias (NeurIPS 2025 · similarity 0.89)
- Algorithmic Stability Unleashed: Generalization Bounds with Unbounded Losses (ICML 2024 · similarity 0.89)
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.