Document Open Access Logo

Mapping the Tradeoffs and Limitations of Algorithmic Fairness

Authors Etam Benger , Katrina Ligett

PDF

File

Thumbnail PDF
PDF
LIPIcs.FORC.2025.19.pdf
  • Filesize: 7.27 MB
  • 20 pages

Document Identifiers

Subject Classification

ACM Subject Classification
  • Theory of computation → Machine learning theory
  • Mathematics of computing → Information theory
  • Social and professional topics → Computing / technology policy
Keywords
  • Algorithmic fairness
  • information theory
  • sufficiency-separation tradeoff

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

Abstract

Sufficiency and separation are two fundamental criteria in classification fairness. For binary classifiers, these concepts correspond to subgroup calibration and equalized odds, respectively, and are known to be incompatible except in trivial cases. In this work, we explore a relaxation of these criteria based on f-divergences between distributions - essentially the same relaxation studied in the literature on approximate multicalibration - analyze their relationships, and derive implications for fair representations and downstream uses (post-processing) of representations. We show that when a protected attribute is determinable from features present in the data, the (relaxed) criteria of sufficiency and separation exhibit a tradeoff, forming a convex Pareto frontier. Moreover, we prove that when a protected attribute is not fully encoded in the data, achieving full sufficiency may be impossible. This finding not only strengthens the case against "fairness through unawareness" but also highlights an important caveat for work on (multi-)calibration.

Cite As Get BibTex

Etam Benger and Katrina Ligett. Mapping the Tradeoffs and Limitations of Algorithmic Fairness. In 6th Symposium on Foundations of Responsible Computing (FORC 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 329, pp. 19:1-19:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025) https://doi.org/10.4230/LIPIcs.FORC.2025.19

Author Details

Etam Benger
  • The Hebrew University of Jerusalem, Israel
Katrina Ligett
  • The Hebrew University of Jerusalem, Israel

Funding

This work was supported in part by a gift to the McCourt School of Public Policy and Georgetown University, Simons Foundation Collaboration 733792, Israel Science Foundation (ISF) grant 2861/20, ERC grant 101125913, and a grant from the Israeli Council for Higher Education. Views and opinions expressed are however those of the authors only and do not necessarily reflect those of the European Union or the European Research Council Executive Agency. Neither the European Union nor the granting authority can be held responsible for them.

Acknowledgements

We thank Flavio Calmon for an insightful suggestion that inspired the formulation using f-information.

References

  1. Solon Barocas, Moritz Hardt, and Arvind Narayanan. Fairness and Machine Learning: Limitations and Opportunities. MIT Press, 2023. Google Scholar
  2. Yahav Bechavod and Katrina Ligett. Penalizing unfairness in binary classification. arXiv preprint arXiv:1707.00044, 2017. Google Scholar
  3. Alex Chouldechova. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. Big Data, 5(2):153-163, October 2016. URL: https://doi.org/10.1089/BIG.2016.0047.
  4. Thomas M. Cover and Joy A. Thomas. Elements of Information Theory. Wiley-Interscience, 2nd ed. edition, 2006. Google Scholar
  5. Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard Zemel. Fairness through awareness. In 3rd Innovations in Theoretical Computer Science Conference (ITCS), pages 214-226, 2012. URL: https://doi.org/10.1145/2090236.2090255.
  6. Parikshit Gopalan, Adam Tauman Kalai, Omer Reingold, Vatsal Sharan, and Udi Wieder. Omnipredictors. In 13th Innovations in Theoretical Computer Science Conference (ITCS), volume 215, pages 79:1-79:21, 2022. URL: https://doi.org/10.4230/LIPICS.ITCS.2022.79.
  7. Faisal Hamman and Sanghamitra Dutta. A unified view of group fairness tradeoffs using partial information decomposition. In 2024 IEEE International Symposium on Information Theory (ISIT), pages 214-219, 2024. URL: https://doi.org/10.1109/ISIT57864.2024.10619698.
  8. Moritz Hardt, Eric Price, and Nathan Srebro. Equality of opportunity in supervised learning. Advances in Neural Information Processing Systems, 29, 2016. Google Scholar
  9. Ursula Hébert-Johnson, Michael Kim, Omer Reingold, and Guy Rothblum. Multicalibration: Calibration for the (computationally-identifiable) masses. In International Conference on Machine Learning, pages 1939-1948. PMLR, 2018. Google Scholar
  10. Toshihiro Kamishima, Shotaro Akaho, and Jun Sakuma. Fairness-aware learning through regularization approach. In 2011 IEEE 11th International Conference on Data Mining Workshops, pages 643-650, 2011. URL: https://doi.org/10.1109/ICDMW.2011.83.
  11. Jon Kleinberg, Sendhil Mullainathan, and Manish Raghavan. Inherent Trade-Offs in the Fair Determination of Risk Scores. In 8th Innovations in Theoretical Computer Science Conference (ITCS), pages 43:1-43:23, 2017. URL: https://doi.org/10.4230/LIPICS.ITCS.2017.43.
  12. Geoff Pleiss, Manish Raghavan, Felix Wu, Jon Kleinberg, and Kilian Q Weinberger. On fairness and calibration. Advances in Neural Information Processing Systems, 30, 2017. Google Scholar
  13. Yury Polyanskiy and Yihong Wu. Information Theory: From Coding to Learning. Cambridge University Press, 2025. Google Scholar
  14. Hans S. Witsenhausen and Aaron D. Wyner. A conditional entropy bound for a pair of discrete random variables. IEEE Transactions on Information Theory, 21(5):493-501, 1975. Google Scholar
  15. Blake Woodworth, Suriya Gunasekar, Mesrob I. Ohannessian, and Nathan Srebro. Learning non-discriminatory predictors. In Conference on Learning Theory, pages 1920-1953. PMLR, 2017. URL: http://proceedings.mlr.press/v65/woodworth17a.html.
  16. Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rodriguez, and Krishna P Gummadi. Fairness beyond disparate treatment & disparate impact: Learning classification without disparate mistreatment. In Proceedings of the 26th International Conference on World Wide Web, pages 1171-1180, 2017. URL: https://doi.org/10.1145/3038912.3052660.
  17. Rich Zemel, Yu Wu, Kevin Swersky, Toniann Pitassi, and Cynthia Dwork. Learning fair representations. In International Conference on Machine Learning, pages 325-333. PMLR, 2013. Google Scholar
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2025 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact