Research map / Optimization / Nonconvex and smooth optimization
Anytime Online-to-Batch, Optimism and Acceleration
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 |
|---|---|---|---|
| Optimistic online learner with hint g_{t-1} combined with anytime online-to-batch (Algorithm 3), versus standard online-to-batch | stochastic smooth convex optimization · L-smooth stochastic convex problems with variance sigma^2 | expected excess loss convergence rate | Helped |
| Adaptive stochastic acceleration reduction (Algorithm 4) applied to any adaptive online learner | stochastic smooth convex optimization · L-smooth stochastic losses with variance sigma^2, adapts to L and sigma without knowing them | expected excess loss convergence rate | Helped |
| Adaptive acceleration reduction (Algorithm 4) applied to non-smooth losses | adaptive online learner under Algorithm 4 · non-smooth stochastic convex losses | convergence rate | No clear effect |
| Weights alpha_t = t in anytime online-to-batch for strongly convex losses | strongly convex stochastic optimization · mu-strongly convex stochastic losses | excess loss bound | Helped |
Closest papers by meaning
- Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality (NeurIPS 2025 · similarity 0.92)
- Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness (NeurIPS 2025 · similarity 0.91)
- Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems (NeurIPS 2026 · similarity 0.90)
- A Reduction from Delayed to Immediate Feedback for Online Convex Optimization with Improved Guarantees (NeurIPS 2026 · similarity 0.90)
- Exploiting Curvature in Online Convex Optimization with Delayed Feedback (ICML 2025 · similarity 0.89)
- Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent (ICML 2025 · 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.