mlsanityData to 14 Oct 2026

Online Learning with an Unknown Fairness Metric

arXiv 1802.06936 ↗First posted 20 Feb 2018cs.LGcited by 62

Not on the map. Why?

Abstract (arXiv)

We consider the problem of online learning in the linear contextual bandits setting, but in which there are also strong individual fairness constraints governed by an unknown similarity metric. These constraints demand that we select similar actions or individuals with approximately equal probability (arXiv:1104.3913), which may be at odds with optimizing reward, thus modeling settings where profit and social policy are in tension. We assume we learn about an unknown Mahalanobis similarity metric from only weak feedback that identifies fairness violations, but does not quantify their extent. This is intended to represent the interventions of a regulator who "knows unfairness when he sees it" but nevertheless cannot enunciate a quantitative fairness metric over individuals. Our main result is an algorithm in the adversarial context setting that has a number of fairness violations that depends only logarithmically on T, while obtaining an optimal O(√T) regret bound to the best fair policy.

Key facts. Cited by 62 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 16; 2022: 14; 2023: 11; 2024: 12; 2025: 3; 2026: 5.

62 papers.

Sort:

By area:

  1. 2020Aligning AI With Shared Human Valuescited by 723
  2. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  3. 2022Fair and Optimal Classification via Post-Processingcited by 51
  4. 2021Fairness of Exposure in Stochastic Banditscited by 43
  5. 2023A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challengescited by 41
  6. 2022Representation Bias in Data: A Survey on Identification and Resolution Techniquescited by 37
  7. 2021Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Informationcited by 33
  8. 2023Swap Agnostic Learning, or Characterizing Omniprediction via Multicalibrationcited by 31
  9. 2021Simple and near-optimal algorithms for hidden stratification and multi-group learningcited by 28
  10. 2021A Sociotechnical View of Algorithmic Fairnesscited by 24
  11. 2021Fair Exploration via Axiomatic Bargainingcited by 22
  12. 2021Fairness-Aware Online Meta-learningcited by 19
38 more
  1. 2022What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspectivecited by 18
  2. 2022Survey on Fair Reinforcement Learning: Theory and Practicecited by 14
  3. 2021Individually Fair Gradient Boostingcited by 12
  4. 2021Beyond "Fairness:" Structural (In)justice Lenses on AI for Educationcited by 12
  5. 2021Bandit Algorithms for Precision Medicinecited by 12
  6. 2021Fairness with Continuous Optimal Transportcited by 10
  7. 2022Uncertainty Quantification for Fairness in Two-Stage Recommender Systemscited by 10
  8. 2022An Efficient Algorithm for Fair Multi-Agent Multi-Armed Bandit with Low Regretcited by 10
  9. 2024Fairness in Reinforcement Learning: A Surveycited by 9
  10. 2022Multi-disciplinary fairness considerations in machine learning for clinical trialscited by 8
  11. 2022Individual Preference Stability for Clusteringcited by 8
  12. 2024No-Regret Learning for Fair Multi-Agent Social Welfare Optimizationcited by 8
  13. 2021Fairness Maximization among Offline Agents in Online-Matching Marketscited by 6
  14. 2023BanditQ: Fair Bandits with Guaranteed Rewardscited by 6
  15. 2021Precarity: Modeling the Long Term Effects of Compounded Decisions on Individual Instabilitycited by 5
  16. 2021Fairer LP-based Online Allocation via Analytic Centercited by 5
  17. 2022Individually Fair Learning with One-Sided Feedbackcited by 5
  18. 2022Human-Guided Fair Classification for Natural Language Processingcited by 5
  19. 2023Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpointcited by 5
  20. 2021Learning to Generate Fair Clusters from Demonstrationscited by 4
  21. 2022FETA: Fairness Enforced Verifying, Training, and Predicting Algorithms for Neural Networkscited by 4
  22. 2023Holistic Survey of Privacy and Fairness in Machine Learningcited by 4
  23. 2024Fair Online Bilateral Tradecited by 4
  24. 2024Long-Term Fairness Inquiries and Pursuits in Machine Learning: A Survey of Notions, Methods, and Challengescited by 4
  25. 2024Keep Everyone Happy: Online Fair Division of Numerous Items with Few Copiescited by 4
  26. 2022It's Not Fairness, and It's Not Fair: The Failure of Distributional Equality and the Promise of Relational Equality in Complete-Information Hiring Gamescited by 3
  27. 2023Enhancing Group Fairness in Online Settings Using Oblique Decision Forestscited by 3
  28. 2023Causal Fair Metric: Bridging Causality, Individual Fairness, and Adversarial Robustnesscited by 3
  29. 2024Monotone Individual Fairnesscited by 3
  30. 2024Fair Best Arm Identification with Fixed Confidencecited by 3
  31. 2025A Design Framework for operationalizing Trustworthy Artificial Intelligence in Healthcare: Requirements, Tradeoffs and Challenges for its Clinical Adoptioncited by 3
  32. 2024Online Learning with Unknown Constraintscited by 2
  33. 2023Pragmatic Fairness: Developing Policies with Outcome Disparity Controlcited by 1
  34. 2023Matrix Estimation for Individual Fairnesscited by 1
  35. 2023FAIRO: Fairness-aware Adaptation in Sequential-Decision Making for Human-in-the-Loop Systemscited by 1
  36. 2024Simultaneously Achieving Group Exposure Fairness and Within-Group Meritocracy in Stochastic Banditscited by 1
  37. 2024IBCB: Efficient Inverse Batched Contextual Bandit for Behavioral Evolution Historycited by 1
  38. 2024Long-Term Fairness in Sequential Multi-Agent Selection with Positive Reinforcementcited by 1

50 most cited of 62 All 62 (JSON)