Research map / Optimization / Implicit bias and generalization
Stochastic Gradient and Langevin Processes
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 the noise covariance in standard SGD | SGD · CIFAR-10 test set | test accuracy | Helped |
| Match noise covariance while changing step size and batch size | SGD · CIFAR-10 test set | test accuracy | No clear effect |
| Inject additional noise to match a higher covariance | Large-noise SGD · CIFAR-10 test set | test accuracy | Helped |
| Use large-noise SGD with noise covariance matched to vanilla SGD | Large-noise SGD versus vanilla SGD · CIFAR-10 test set | test accuracy | No clear effect |
Closest papers by meaning
- Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization (NeurIPS 2022 · similarity 0.91)
- Generalization of noisy SGD in unbounded non-convex settings (ICML 2025 · similarity 0.91)
- The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations (ICML 2025 · similarity 0.91)
- Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization (NeurIPS 2018 · similarity 0.90)
- What is the Long-Run Distribution of Stochastic Gradient Descent? A Large Deviations Analysis (ICML 2024 · similarity 0.89)
- High-dimensional Limit of SGD for Diagonal Linear Networks (NeurIPS 2026 · 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.