Research map / Optimization / Nonconvex and smooth optimization
SGD without Replacement: Sharper Rates for General Smooth Convex Functions
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 |
|---|---|---|---|
| sample without replacement rather than with replacement | SGD on general smooth strongly-convex functions with large K · General smooth strongly-convex functions, large K | suboptimality: O\left(\tfrac{1}{nK}\right) -> \tilde{O}\left(\tfrac{1}{nK^2}\right) | Helped |
| sample without replacement rather than with replacement | SGD on general smooth strongly-convex functions with small K · General smooth strongly-convex functions, small K | suboptimality: O\left(\tfrac{1}{nK}\right) -> O\left(\tfrac{1}{nK} \right) | No clear effect |
| sample without replacement rather than with replacement | SGD on general smooth convex functions without strong convexity · General smooth convex functions without strong convexity | suboptimality: O(G\cdot D/\sqrt{nK}) -> O\left(\tfrac{1}{\sqrt{nK}} \right) | No clear effect |
| remove smoothness from the assumptions | SGDo on strongly-convex functions · Strongly-convex functions | suboptimality: G^2/(8\mu nK) | Hurt |
Closest papers by meaning
- Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions (NeurIPS 2025 · similarity 0.93)
- Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization (NeurIPS 2025 · similarity 0.89)
- The Sample Complexity of Gradient Descent in Stochastic Convex Optimization (NeurIPS 2024 · similarity 0.88)
- Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity (ICLR 2025 · similarity 0.88)
- Universal Gradient Methods for Stochastic Convex Optimization (ICML 2024 · similarity 0.88)
- Directional Smoothness and Gradient Methods: Convergence and Adaptivity (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.