Research map / Bandits and online learning / Online convex optimization and games
A Simple yet Universal Strategy for Online 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 |
|---|---|---|---|
| Replace per-type surrogate losses with black-box experts run on original functions, aggregated by Adapt-ML-Prod meta-algorithm over linearized losses (USC) | online convex optimization with strongly convex functions · synthetic online convex problems (Figure 1a) | regret | Helped |
| Replace per-type surrogate losses with black-box experts run on original functions, aggregated by Adapt-ML-Prod meta-algorithm over linearized losses (USC) | online convex optimization with general convex functions · synthetic online convex problems (Figure 1b) | regret | Helped |
| Use a geometric grid of O(log T) candidate strong-convexity/exp-concavity values for experts | USC expert construction · theoretical analysis | regret overhead | No clear effect |
Closest papers by meaning
- Universal Online Convex Optimization with $1$ Projection per Round (NeurIPS 2024 · similarity 0.94)
- Small-loss Adaptive Regret for Online Convex Optimization (ICML 2024 · similarity 0.92)
- Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets (NeurIPS 2024 · similarity 0.89)
- Dynamic Regret Reduces to Kernelized Static Regret (NeurIPS 2025 · similarity 0.89)
- A Simple and Optimal Approach for Universal Online Learning with Gradient Variations (NeurIPS 2024 · similarity 0.89)
- A Reduction from Delayed to Immediate Feedback for Online Convex Optimization with Improved Guarantees (NeurIPS 2026 · 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.