Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Online Learning with an Unknown Fairness Metric
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 |
|---|---|---|---|
| Learn the unknown Mahalanobis fairness metric from violation-only oracle feedback while choosing actions optimistically | L_full · Adversarial linear contextual bandits | regret: O\left(k^2d^2 \log\left(\frac{d \cdot ||A^\top A||_F }{\epsilon}\right) + k^3\epsilon T + d\sqrt{T}\log(\frac{T}{\delta} | Helped |
| Learn the unknown Mahalanobis fairness metric from violation-only oracle feedback | L_full · Adversarial linear contextual bandits | fairness loss: O\left(k^2d^2 \log\left(\frac{d \cdot ||A^\top A||_F }{\epsilon}\right)\right) | Helped |
| Use upper confidence bounds for rewards and distance-estimator subroutines for fairness distances | L_full · Adversarial linear contextual bandits | regret: O\left(k^2d^2 \log\left(\frac{d \cdot ||A^\top A||_F }{\epsilon}\right) + k^3\epsilon T + d\sqrt{T}\log(\frac{T}{\delta} | Helped |
| Permit up to k actions per round instead of selecting a single action | L_full_m · Multiple actions per round | regret: O\left(k^3d^2 \log\left(\frac{d \cdot ||A^\top A||_F }{\epsilon}\right) + k^3\epsilon T + dk\sqrt{k^2T}\log(\frac{kT}{\d | Mixed |
Closest papers by meaning
- Metric-Free Individual Fairness in Online Learning (NeurIPS 2020 · similarity 0.90)
- Fairness in Learning: Classic and Contextual Bandits (NeurIPS 2016 · similarity 0.90)
- Honor Among Bandits: No-Regret Learning for Online Fair Division (NeurIPS 2024 · similarity 0.87)
- No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need! (NeurIPS 2025 · similarity 0.85)
- Efficient Contextual Bandits with Uninformed Feedback Graphs (ICML 2024 · similarity 0.85)
- Direction-Aware Offline-to-Online Learning in Linear Contextual Bandits (NeurIPS 2026 · 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.