Research map / Bandits and online learning / Multi-armed bandits
My Fair Bandit: Distributed Learning of Max-Min Fairness with Multi-player 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 |
|---|---|---|---|
| Use the epoch-based distributed max-min fairness algorithm with exploration, matching, consensus, and exploitation phases | Multi-player bandits with heterogeneous rewards and no communication · General problem | expected regret | Helped |
| Optimize sum of rewards instead of max-min fairness | Multi-player bandit allocation · U1 (N=4) | max-min regret: \Omega\left(\frac{T}{4}\right) | Hurt |
| Optimize sum of rewards instead of max-min fairness | Multi-player bandit allocation · U2 (N=10) | max-min regret: \Omega\left(\frac{T}{10}\right) | Hurt |
| Warm-start the matching phase from the last exploitation action when eligible (ablation) | My Fair Bandit · U1 and U2 simulations | practical performance | Helped |
| Multiply confidence intervals by 0.01 (ablation) | My Fair Bandit · U1 and U2 simulations | practical performance | Helped |
Closest papers by meaning
- Optimal Algorithm for Max-Min Fair Bandit (ICML 2025 · similarity 0.93)
- Honor Among Bandits: No-Regret Learning for Online Fair Division (NeurIPS 2024 · similarity 0.92)
- Distributed Multi-Player Bandits - a Game of Thrones Approach (NeurIPS 2018 · similarity 0.92)
- Improved Regret Bounds for Online Fair Division with Bandit Learning (AAAI 2025 · similarity 0.91)
- Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks (NeurIPS 2025 · similarity 0.89)
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret (NeurIPS 2026 · 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.