Research map / Optimization / Implicit bias and generalization
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms
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 |
|---|---|---|---|
| Estimate the invariant-measure complexity R from SGD iterates | VGG11 and FCNs · CIFAR10, SVHN, BHP | correlation with generalization error: p-value ≪ 0.001 | Mixed |
| Increase the step-size η | SGD · BHP | complexity R | Hurt |
| Estimate complexity R as a predictor of generalization error | Classification models with cross-entropy loss · CIFAR10 and SVHN | correlation with generalization error | No clear effect |
Closest papers by meaning
- Generalization at the Edge of Stability (NeurIPS 2026 · similarity 0.92)
- On the Limitations of Fractal Dimension as a Measure of Generalization (NeurIPS 2024 · similarity 0.91)
- Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers (ICML 2022 · similarity 0.90)
- Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms (NeurIPS 2024 · similarity 0.90)
- Generalization Bounds for Heavy-Tailed SDEs through the Fractional Fokker-Planck Equation (ICML 2024 · similarity 0.88)
- The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations (ICML 2025 · 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.