mlsanityData to 14 Oct 2026

Algorithmic Fairness: A Runtime Perspective

arXiv 2507.20711 ↗First posted 28 Jul 2025cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Fairness in AI is traditionally studied as a static property evaluated once, over a fixed dataset. However, real-world AI systems operate sequentially, with outcomes and environments evolving over time. This paper proposes a framework for analysing fairness as a runtime property. Using a minimal yet expressive model based on sequences of coin tosses with possibly evolving biases, we study the problems of monitoring and enforcing fairness expressed in either toss outcomes or coin biases. Since there is no one-size-fits-all solution for either problem, we provide a summary of monitoring and enforcement strategies, parametrised by environment dynamics, prediction horizon, and confidence thresholds. For both problems, we present general results under simple or minimal assumptions. We survey existing solutions for the monitoring problem for Markovian and additive dynamics, and existing solutions for the enforcement problem in static settings with known dynamics.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 44 references that are in the map. First posted on arXiv 28 Jul 2025.

Builds on

25 of 44 references.

References · 25

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  2. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  3. 2017Counterfactual Fairnesscited by 804
  4. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 384
  5. 2017Fairness in Criminal Justice Risk Assessments: The State of the Artcited by 315
  6. 2018Time-uniform, nonparametric, nonasymptotic confidence sequencescited by 229
  7. 2019The What-If Tool: Interactive Probing of Machine Learning Modelscited by 207
  8. 2018Delayed Impact of Fair Machine Learningcited by 184
  9. 2018Differentially Private Fair Learningcited by 76
  10. 2019On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learningcited by 49
  11. 2020Verifying Individual Fairness in Machine Learning Modelscited by 49
  12. 2019Average Individual Fairness: Algorithms, Generalization and Experimentscited by 46
13 more
  1. 2018Probabilistic Verification of Fairness Properties via Concentrationcited by 45
  2. 2021Fair Normalizing Flowscited by 38
  3. 2020Justicia: A Stochastic SAT Approach to Formally Verify Fairnesscited by 25
  4. 2021Certifying Robustness to Programmable Data Bias in Decision Treescited by 21
  5. 2021Fairness-Aware PAC Learning from Corrupted Datacited by 18
  6. 2021Probabilistic Verification of Neural Networks Against Group Fairnesscited by 17
  7. 2023Runtime Monitoring of Dynamic Fairness Propertiescited by 17
  8. 2021Algorithmic Fairness Verification with Graphical Modelscited by 16
  9. 2017Real-time Stream-based Monitoringcited by 13
  10. 2023Monitoring Algorithmic Fairnesscited by 8
  11. 2023Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Makingcited by 8
  12. 2023Monitoring Algorithmic Fairness under Partial Observationscited by 7
  13. 2024Fairness Shields: Safeguarding against Biased Decision Makerscited by 5

Built on by

Not cited yet.