Research map / Optimization / Nonconvex and smooth optimization
Obtaining Adjustable Regularization for Free via Iterate Averaging
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 |
|---|---|---|---|
| Add epoch-wise averaging of saved SGD checkpoints | VGG-16 · CIFAR-10 | accuracy: $92.54$\pm 0.22$ -> $\bm{93.18}$\pm 0.06$ | Helped |
| Add epoch-wise averaging of saved SGD checkpoints | ResNet-18 · CIFAR-10 | accuracy: $94.54$\pm 0.04$ -> $\bm{94.72}$\pm 0.04$ | Helped |
| Add epoch-wise averaging of saved SGD checkpoints | ResNet-18 · CIFAR-100 | accuracy: $75.62$\pm 0.16$ -> $\bm{76.24}$\pm 0.05$ | Helped |
Closest papers by meaning
- The Benefits of Implicit Regularization from SGD in Least Squares Problems (NeurIPS 2021 · similarity 0.90)
- Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization (NeurIPS 2025 · similarity 0.88)
- Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression (NeurIPS 2024 · similarity 0.88)
- Generalization Analysis of Stochastic Weight Averaging with General Sampling (ICML 2024 · similarity 0.87)
- Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime (NeurIPS 2025 · similarity 0.86)
- Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson–Romberg Extrapolation (ICLR 2025 · similarity 0.86)
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.