Research map / Bandits and online learning / Multi-armed bandits
Achieving Fairness in the Stochastic Multi-Armed Bandit Problem
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 |
|---|---|---|---|
| Wrap a learning algorithm with Fair-Learn's quota-enforcement rule | Fair-MAB algorithms · Fair-MAB | fairness guarantee: α-fair | Helped |
| Use UCB1 as the Fair-Learn black-box learner | Fair-Learn · Fair-MAB | r-Regret: O(√(T ln T)); for large enough T, ℛ^r_Fair-ucb(T) ≤ (1 + π²/3) · ∑_{i ∈ [k]}Δ_i | Helped |
| Increase the unfairness tolerance α | Fair-ucb · Synthetic Fair-MAB instance, T = 10^6 | conventional regret | Helped |
| Increase the unfairness tolerance α | Fair-ucb · Synthetic Fair-MAB instance, T = 10^6 | maximum fairness violation | Hurt |
| Use horizon-aware quota satisfaction followed by UCB1 | Fair-MAB · Fair-MAB | r-Regret: O(ln T) | Helped |
| Compare Fair-ucb with LFG | Fair-ucb · Synthetic Fair-MAB instance | r-Regret | No clear effect |
| Use Fair-ucb instead of LFG | Fair-MAB · Fairness over time | maximum fairness violation | Helped |
Closest papers by meaning
- Optimal Algorithm for Max-Min Fair Bandit (ICML 2025 · similarity 0.91)
- Honor Among Bandits: No-Regret Learning for Online Fair Division (NeurIPS 2024 · similarity 0.90)
- Improved Regret Bounds for Online Fair Division with Bandit Learning (AAAI 2025 · similarity 0.90)
- p-Mean Regret for Stochastic Bandits (AAAI 2025 · similarity 0.89)
- No-Regret Learning for Fair Multi-Agent Social Welfare Optimization (NeurIPS 2024 · similarity 0.89)
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret (NeurIPS 2026 · 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.