Research map / Bandits and online learning / Online convex optimization and games
Better Bounds for the Distributed Experts Problem
David Woodruff, Samson Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| use the distributed exponential-scaling protocol instead of offline MWU | distributed experts protocol · HPO-B (models as experts, datasets as servers) | reward | Improved |
| raise the communication threshold, p>1 (ablation) | distributed experts protocol · HPO-B | total communication | Hurt |
| raise the communication threshold, p<1 (ablation) | distributed experts protocol · HPO-B | total communication | Improved |
Closest papers by meaning
- Communication Bounds for the Distributed Experts Problem (NeurIPS 2024 · similarity 0.94)
- On Interpolating Experts and Multi-Armed Bandits (ICML 2024 · similarity 0.86)
- A second order regret bound for NormalHedge (NeurIPS 2026 · similarity 0.85)
- Individual Regret in Cooperative Stochastic Multi-Armed Bandits (NeurIPS 2025 · similarity 0.84)
- Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks (NeurIPS 2025 · similarity 0.84)
- When Lower-Order Terms Dominate: Adaptive Expert Algorithms for Heavy-Tailed Losses (NeurIPS 2025 · similarity 0.84)
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.
