mlsanityData to 7 Oct 2026

From Utilitarian to Rawlsian Designs for Algorithmic Fairness

arXiv 2302.03567 ↗First posted 7 Feb 2023cs.CY cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

There is a lack of consensus within the literature as to how `fairness' of algorithmic systems can be measured, and different metrics can often be at odds. In this paper, we approach this task by drawing on the ethical frameworks of utilitarianism and John Rawls. Informally, these two theories of distributive justice measure the `good' as either a population's sum of utility, or worst-off outcomes, respectively. We present a parameterized class of objective functions that interpolates between these two (possibly) conflicting notions of the `good'. This class is shown to represent a relaxation of the Rawlsian `veil of ignorance', and its sequence of optimal solutions converges to both a utilitarian and Rawlsian optimum. Several other properties of this class are studied, including: 1) a relationship to regularized optimization, 2) feasibility of consistent estimation, and 3) algorithmic cost. In several real-world datasets, we compute optimal solutions and construct the tradeoff between utilitarian and Rawlsian notions of the `good'. Empirically, we demonstrate that increasing model complexity can manifest strict improvements to both measures of the `good'. This work suggests that the proper degree of `fairness' can be informed by a designer's preferences over the space of induced utilitarian and Rawlsian `good'.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 61 references that are in the map. First posted on arXiv 7 Feb 2023.

Builds on

20 of 61 references.

References · 20

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  2. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  3. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 582
  4. 2017Algorithmic decision making and the cost of fairnesscited by 402
  5. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 381
  6. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  7. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  8. 2018Delayed Impact of Fair Machine Learningcited by 183
  9. 2020Minimax Pareto Fairness: A Multi Objective Perspectivecited by 152
  10. 2017A Convex Framework for Fair Regressioncited by 147
  11. 2020Tilted Empirical Risk Minimizationcited by 103
  12. 2018A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunitycited by 53
8 more
  1. 2018Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Makingcited by 46
  2. 2019Average Individual Fairness: Algorithms, Generalization and Experimentscited by 46
  3. 2021Emergent Unfairness in Algorithmic Fairness-Accuracy Trade-Off Researchcited by 34
  4. 2020On the Moral Justification of Statistical Paritycited by 30
  5. 2022Minimax Demographic Group Fairness in Federated Learningcited by 24
  6. 2022Minimax AUC Fairness: Efficient Algorithm with Provable Convergencecited by 16
  7. 2022To the Fairness Frontier and Beyond: Identifying, Quantifying, and Optimizing the Fairness-Accuracy Pareto Frontiercited by 10
  8. 2021RAWLSNET: Altering Bayesian Networks to Encode Rawlsian Fair Equality of Opportunitycited by 4

Built on by

Not cited yet.