Research map / Optimization / Nonconvex and smooth optimization
Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression
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 tail geometric stepsize decay (halve stepsize every K steps) with last iterate SGD instead of polynomial decay | last iterate SGD in overparameterized linear regression · instance-wise risk comparison (theory) | excess risk | No clear effect |
| Add tail geometric stepsize decay to last iterate SGD (vs. constant stepsize) | last iterate SGD, linear regression · overparameterized linear regression, theory | excess risk bound order | Helped |
| Use tail geometric stepsize decay with the last iterate, vs. constant stepsize with averaging | last iterate SGD · theory comparison with iterate averaging | excess risk bound | No clear effect |
Closest papers by meaning
- Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime (NeurIPS 2025 · similarity 0.91)
- Risk Bounds of Accelerated SGD for Overparameterized Linear Regression (ICLR 2024 · similarity 0.91)
- Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization (ICML 2025 · similarity 0.89)
- Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods (ICLR 2024 · similarity 0.88)
- Learning Curves of Stochastic Gradient Descent in Kernel Regression (ICML 2025 · similarity 0.88)
- Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression (NeurIPS 2024 · 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.