Research map / Optimization / Nonconvex and smooth optimization
Local Minimax Complexity of Stochastic Convex Optimization
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 |
|---|---|---|---|
| SGD with stepsize 1/t instead of 1/sqrt(t) | SGD on symmetric functions f_k · simulation, k=2 vs k=3 | convergence rate relative to local minimax benchmark | Mixed |
| Adaptive stochastic sign-testing binary search instead of SGD | 1D symmetric and asymmetric convex functions · simulation with noise sigma=0.1, T from 100 to 10,000 | averaged error vs local minimax benchmark rate | Helped |
| Restricting the stepsize to 1/t or 1/sqrt(t) without adapting to function curvature | SGD on k=3/2 functions · simulation | convergence rate vs optimal | No clear effect |
Closest papers by meaning
- Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing (ICML 2024 · similarity 0.90)
- The Sample Complexity of Gradient Descent in Stochastic Convex Optimization (NeurIPS 2024 · similarity 0.90)
- Universal Gradient Methods for Stochastic Convex Optimization (ICML 2024 · similarity 0.89)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.89)
- Stochastic Weakly Convex Optimization beyond Lipschitz Continuity (ICML 2024 · similarity 0.89)
- Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity (NeurIPS 2024 · 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.