Shizhou Xu

Shizhou Xu

Working on the interdisciplinary area between mathematics and machine learning.

On the (In)Compatibility between Individual and Group Fairness

Published in Under review (SIAM Journal on Mathematics of Data Science — SIMODS), 2024

Summary

Fairness requirements in ML are often stated at different levels:

  • Individual fairness (similar individuals should be treated similarly), and
  • Group fairness (aggregate parity constraints across groups).

This work provides a mathematical characterization of when these objectives are compatible and when they are provably in tension, guiding both theory and practical design choices.

Resources

  • Paper (PDF): https://arxiv.org/pdf/2401.07174
  • Code: (add link when public)

Recommended citation: Shizhou Xu, Thomas Strohmer. (2024). “On the (In)Compatibility between Individual and Group Fairness.” Under review at SIAM Journal on Mathematics of Data Science.
Download Paper | Download Slides