Research map / Bandits and online learning / Online convex optimization and games
Distributed Projection-Free Online Learning for Smooth and Convex Losses
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 |
|---|---|---|---|
| Exploit smoothness of the losses | D-OSPA · D-OCO, smooth and convex losses | regret bound: O(T^{3/4}) -> O(T^{2/3}) | Helped |
| Use sampling and blocking together with m = k | D-OSPA · D-OCO | linear optimizations per round on average: one linear optimization per round on average | Helped |
| Use the smooth-and-convex configuration rather than the general-convex configuration (ablation) | D-OSPA · aloi | average loss | Helped |
| Use the smooth-and-convex configuration rather than the general-convex configuration (ablation) | D-OSPA · shuttle | average loss | Helped |
| Use the general-convex configuration instead of the smooth-and-convex configuration (ablation) | D-OSPA · aloi and shuttle | average loss | No clear effect |
Closest papers by meaning
- Revisiting Projection-Free Online Learning with Time-Varying Constraints (AAAI 2025 · similarity 0.93)
- Universal Online Convex Optimization with $1$ Projection per Round (NeurIPS 2024 · similarity 0.90)
- Projection-Free Online Convex Optimization with Time-Varying Constraints (ICML 2024 · similarity 0.90)
- Distributed Online Convex Optimization with Compressed Communication: Optimal Regret and Applications (NeurIPS 2026 · similarity 0.89)
- Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements (ICML 2024 · similarity 0.89)
- Non-stationary Projection-Free Online Learning with Dynamic and Adaptive Regret Guarantees (AAAI 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.