Research map / Optimization / Implicit bias and generalization
An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias
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 constant step size from 0.2 to 0.3 or larger | constant step size SGD · non-convex log-loss example | asymptotic bias of SGD | Hurt |
| decrease constant step size | constant step size SGD · Blake-Zisserman example | asymptotic bias of SGD | Helped |
Closest papers by meaning
- Asymptotic theory of SGD with a general learning-rate (NeurIPS 2025 · similarity 0.92)
- Normalized SGD in the Convex Regime: First High-Probability Guarantees and Momentum Extension (NeurIPS 2026 · similarity 0.91)
- Universal Stagewise Learning for Non-Convex Problems with Convergence on Averaged Solutions (ICLR 2019 · similarity 0.91)
- Robustness Analysis of Non-Convex Stochastic Gradient Descent using Biased Expectations (NeurIPS 2020 · similarity 0.91)
- Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson–Romberg Extrapolation (ICLR 2025 · similarity 0.91)
- Statistical Guarantees for High-Dimensional Stochastic Gradient Descent (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.