The Implicit Fairness Criterion of Unconstrained Learning
Lydia T. Liu · Max Simchowitz · University of California Moritz Hardt

Tue Jun 11th 04:40 -- 05:00 PM @ Room 103

We clarify what fairness guarantees we can and cannot expect to follow from unconstrained machine learning. Specifically, we show that in many settings, unconstrained learning on its own implies group calibration, that is, the outcome variable is conditionally independent of group membership given the score. A lower bound confirms the optimality of our upper bound. Moreover, we prove that as the excess risk of the learned score decreases, the more strongly it violates separation and independence, two other standard fairness criteria. Our results challenge the view that group calibration necessitates an active intervention, suggesting that often we ought to think of it as a byproduct of unconstrained machine learning.

Author Information

Lydia T. Liu (University of California Berkeley)
Max Simchowitz (UC Berkeley)
University of California Moritz Hardt (University of California, Berkeley)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors