Research map / Bandits and online learning / Multi-armed bandits
Fair Exploration via Axiomatic Bargaining
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 Nash-fair policy PF-UCB instead of regret-optimal KL-UCB | grouped K-armed bandit · 2-group 3-arm synthetic, T=3000 | total regret: +4.7% total regret | Hurt |
| use PF-UCB instead of KL-UCB | grouped K-armed bandit · 2-group 3-arm synthetic, T=3000 | regret of group A (burden of exploration) | Helped |
| use PF-UCB instead of KL-UCB | grouped K-armed bandit · 2-group 3-arm synthetic | finite-time Nash social welfare | Helped |
| use fair PF-OAM instead of regret-optimal OAM | grouped linear contextual bandit · Warfarin race groups, total | utility gain: 100.4 -> 99.6 | Hurt |
| use fair PF-OAM instead of regret-optimal OAM | grouped linear contextual bandit · Warfarin race group C | utility gain: 7.6 -> 24.6 | Helped |
| use fair PF-OAM instead of regret-optimal OAM | grouped linear contextual bandit · Warfarin race group B | utility gain: 69.2 -> 49.4 | Hurt |
| use fair PF-OAM instead of regret-optimal OAM | grouped linear contextual bandit · Warfarin age groups, total | utility gain: 68.0 -> 64.1 | Hurt |
| use fair PF-OAM instead of regret-optimal OAM | grouped linear contextual bandit · Warfarin age >=70 | utility gain: 54.9 -> 48.7 | Hurt |
| use fair PF-OAM instead of regret-optimal OAM | grouped linear contextual bandit · Warfarin age <70 | utility gain: 13.1 -> 15.4 | Helped |
| increase number of groups G in i.i.d. random instances | PF-UCB price of fairness · synthetic i.i.d. instances | median PoF: 0.073 -> 0.015 | Helped |
| increase number of groups G in skewed instances | PF-UCB price of fairness · synthetic skewed instances | median PoF: 0.327 -> 0.521 | Hurt |
Closest papers by meaning
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret (NeurIPS 2026 · similarity 0.90)
- Fairness and Welfare Quantification for Regret in Multi-Armed Bandits (AAAI 2023 · similarity 0.90)
- Honor Among Bandits: No-Regret Learning for Online Fair Division (NeurIPS 2024 · similarity 0.89)
- Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts (NeurIPS 2025 · similarity 0.88)
- No-Regret Learning for Fair Multi-Agent Social Welfare Optimization (NeurIPS 2024 · similarity 0.88)
- Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals (ICML 2024 · similarity 0.87)
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.