Research map / Optimization / Implicit bias and generalization
On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems
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 a 1/run step-size schedule instead of a constant or 1/sqrt(run) schedule | SGD · Shekel risk benchmark | convergence speed: 2 to 4 orders of magnitude | Helped |
| Use a constant step size initially, then switch to 1/run for the remaining training | ResNet18 · CIFAR10 | training loss | Helped |
Closest papers by meaning
- The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations (ICML 2025 · similarity 0.92)
- Derivatives of Stochastic Gradient Descent in parametric optimization (NeurIPS 2024 · similarity 0.91)
- Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems (NeurIPS 2026 · similarity 0.91)
- Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods (ICLR 2024 · similarity 0.91)
- Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime (NeurIPS 2025 · similarity 0.90)
- Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization (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.