Research map / Bandits and online learning / Multi-armed bandits
Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits
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 |
|---|---|---|---|
| Partition the communication graph into center-led components and let each center learn from losses observed by its neighbors | Cooperative nonstochastic multi-armed bandits with a known graph · Nonstochastic cooperative MAB, informed graph | individual expected regret upper bound: 12\sqrt{\left(\ln K\right)\left(1+\frac{K}{\left|\mathcal{N}\left(v\right)\right|}\right)T} | Helped |
| Compute centers distributively using degree groups and 2-MIS selection before running the center-based policy | Cooperative nonstochastic multi-armed bandits with an unknown graph · Nonstochastic cooperative MAB, uninformed graph | individual expected regret upper bound: 12\left(K\ln\left(K^{2}\bar{N}T\right)+\sqrt{\left(\ln K\right)\left(1+\frac{K}{\left|\mathcal{N}\left(v\right)\right|}\ | Helped |
| Use the uninformed rather than informed graph-partitioning procedure | Center-based cooperative MAB · Nonstochastic cooperative MAB | individual expected regret upper bound: 12\left(K\ln\left(K^{2}\bar{N}T\right)+\sqrt{\left(\ln K\right)\left(1+\frac{K}{\left|\mathcal{N}\left(v\right)\right|}\ | Hurt |
Closest papers by meaning
- Individual Regret in Cooperative Stochastic Multi-Armed Bandits (NeurIPS 2025 · similarity 0.95)
- Distributed Bandit Learning: Near-Optimal Regret with Efficient Communication (ICLR 2020 · similarity 0.92)
- Distributed Linear Bandits under Communication Constraints (ICML 2023 · similarity 0.92)
- Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks (NeurIPS 2025 · similarity 0.91)
- Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits (AAAI 2024 · similarity 0.91)
- On Interpolating Experts and Multi-Armed Bandits (ICML 2024 · similarity 0.88)
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.