Research map / Bandits and online learning / Multi-armed bandits
Fairness of Exposure in Stochastic 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 merit-proportional stochastic exposure policies rather than conventional reward-maximizing bandit policies | Stochastic MAB and linear bandits · Yeast and Yahoo! Today Module | fairness regret | Helped |
| Use FairXUCB instead of the conventional UCB algorithm | Stochastic MAB · Yeast | fairness regret | Helped |
| Use FairXTS instead of the conventional TS algorithm | Stochastic MAB · Yeast | fairness regret | Helped |
| Use FairXUCB | Stochastic MAB · Yeast | reward regret | Mixed |
| Use merit-based fair policies with FairX algorithms | Linear bandits · Yeast and Yahoo! Today Module | fairness regret | Helped |
| Use FairXTS rather than FairXUCB's constrained optimism optimization | Stochastic MAB · Stochastic MAB | fairness regret | No clear effect |
| Use FairXLinTS rather than FairXLinUCB's constrained optimism optimization | Stochastic linear bandits · Stochastic linear bandits | fairness regret | No clear effect |
| Require minimum merit and bounded Lipschitz continuity of the merit function | FairX bandit algorithms · Stochastic MAB | fairness regret: 0.015 \TimeSteps | Helped |
Closest papers by meaning
- Achieving Fairness in the Stochastic Multi-Armed Bandit Problem (AAAI 2020 · similarity 0.92)
- Honor Among Bandits: No-Regret Learning for Online Fair Division (NeurIPS 2024 · similarity 0.89)
- Improved Regret Bounds for Online Fair Division with Bandit Learning (AAAI 2025 · similarity 0.89)
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret (NeurIPS 2026 · similarity 0.88)
- On Weak Regret Analysis for Dueling Bandits (NeurIPS 2024 · similarity 0.88)
- Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits (ICLR 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.