mlsanityData to 7 Oct 2026

Price of Fairness in Short-Term and Long-Term Algorithmic Selections

arXiv 2605.06227 ↗First posted 7 May 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Algorithmic decision-making in high-stakes settings can have profound impacts on individuals and populations. While much prior work studies fairness in static settings, recent results show that enforcing static fairness constraints may exacerbate long-run disparities. Motivated by this tension, we study a stylized sequential selection problem in which a decision-maker repeatedly selects individuals, affecting both immediate utility and the population distribution over time. We introduce notions of group fairness for both the short and long term and theoretically analyze the trade-off between fairness and utility via the Price of Fairness (PoF). We characterize optimal and fair policies in the short term and show that the PoF can be large even when group distributions are nearly identical. In contrast, we show that long-term disparities can vanish under simple investment policies that achieve a low PoF. We also empirically validate these theoretical observations using both synthetic and real datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 61 references that are in the map. First posted on arXiv 7 May 2026.

Builds on

44 of 61 references.

References · 44

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  2. 2017Constrained Policy Optimizationcited by 928
  3. 2017Algorithmic decision making and the cost of fairnesscited by 402
  4. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 381
  5. 2017Fairness in Criminal Justice Risk Assessments: The State of the Artcited by 315
  6. 2015Strategic Classificationcited by 256
  7. 2018Delayed Impact of Fair Machine Learningcited by 183
  8. 2016Fairness in Learning: Classic and Contextual Banditscited by 167
  9. 2020Provably Efficient Safe Exploration via Primal-Dual Policy Optimizationcited by 131
  10. 2017Strategic Classification from Revealed Preferencescited by 126
  11. 2018The Measure and Mismeasure of Fairnesscited by 94
  12. 2016Fairness in Reinforcement Learningcited by 93
32 more
  1. 2018How Do Classifiers Induce Agents To Invest Effort Strategically?cited by 82
  2. 2021Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPscited by 78
  3. 2020How Do Fair Decisions Fare in Long-term Qualification?cited by 59
  4. 2018A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunitycited by 53
  5. 2019Algorithms for Fairness in Sequential Decision Makingcited by 53
  6. 2019On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learningcited by 48
  7. 2017Calibrated Fairness in Banditscited by 42
  8. 2021State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewardscited by 37
  9. 2018From Fair Decision Making to Social Equalitycited by 36
  10. 2018Fair Algorithms for Learning in Allocation Problemscited by 29
  11. 2023Long-Term Fairness with Unknown Dynamicscited by 25
  12. 2021Fair Classification with Adversarial Perturbationscited by 23
  13. 2024Truly No-Regret Learning in Constrained MDPscited by 23
  14. 2019Group-Fairness in Influence Maximizationcited by 21
  15. 2022Achieving Long-Term Fairness in Sequential Decision Makingcited by 18
  16. 2019Fairness and Utilization in Allocating Resources with Uncertain Demandcited by 16
  17. 2022Enabling Long-term Fairness in Dynamic Resource Allocationcited by 15
  18. 2020Fair Influence Maximization: A Welfare Optimization Approachcited by 12
  19. 2020Cross-Loss Influence Functions to Explain Deep Network Representationscited by 12
  20. 2021Allocating Opportunities in a Dynamic Model of Intergenerational Mobilitycited by 12
  21. 2021Towards Return Parity in Markov Decision Processescited by 12
  22. 2025A Survey on Explainable Deep Reinforcement Learningcited by 12
  23. 2022Reinforcement Learning with Stepwise Fairness Constraintscited by 9
  24. 2023No-regret Algorithms for Fair Resource Allocationcited by 9
  25. 2024Fairness in Reinforcement Learning: A Surveycited by 9
  26. 2023Designing Long-term Group Fair Policies in Dynamical Systemscited by 8
  27. 2021Long-Term Resource Allocation Fairness in Average Markov Decision Process (AMDP) Environmentcited by 6
  28. 2025Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spacescited by 5
  29. 2020Pipeline Interventionscited by 4
  30. 2022There is no Accuracy-Interpretability Tradeoff in Reinforcement Learning for Mazescited by 4
  31. 2022Wealth Dynamics Over Generations: Analysis and Interventionscited by 2
  32. 2025Policy Design in Long-Run Welfare Dynamicscited by 2

Built on by

Not cited yet.