Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Offline Contextual Bandits with High Probability Fairness Guarantees
Blossom Metevier, Stephen Giguere, Sarah Brockman, Ari Kobren, Yuriy Brun, Emma Brunskill, Philip S. Thomas
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 |
|---|---|---|---|
| Add a safety test on held-out data (RobinHood) instead of enforcing the estimated fairness constraint on all data (NaiveFairBandit) | NaiveFairBandit · tutoring, loan approval, recidivism | fairness violation rate (delta=5%) | Improved |
| Use RobinHood fairness-constrained offline bandit instead of fairness-unaware POEM and Offset Tree | POEM and Offset Tree · similar proportions tutoring, loan, recidivism | off-policy reward | No clear effect |
| Use RobinHood instead of POEM and Offset Tree when the biased option maximizes reward | POEM and Offset Tree · skewed proportions tutoring | fairness violation rate | Improved |
| Allow returning No Solution Found when data is insufficient | RobinHood · all experiments | solution rate | Mixed |
Closest papers by meaning
- Fairness in Learning: Classic and Contextual Bandits (NeurIPS 2016 · similarity 0.90)
- Fairness of Exposure in Stochastic Bandits (ICML 2021 · similarity 0.88)
- A Causal Decomposition Approach for Fair Contextual Multi-Armed Bandits (ICML 2026 · similarity 0.88)
- Honor Among Bandits: No-Regret Learning for Online Fair Division (NeurIPS 2024 · similarity 0.86)
- Improved Regret Bounds for Online Fair Division with Bandit Learning (AAAI 2025 · similarity 0.85)
- Causal Logistic Bandits with Counterfactual Fairness Constraints (ICML 2025 · similarity 0.85)
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.
