TY - GEN
T1 - The implicit fairness criterion of unconstrained learning
AU - Liu, Lydia T.
AU - Simchowitz, Max
AU - Hardt, Moritz
N1 - Publisher Copyright:
© 36th International Conference on Machine Learning, ICML 2019. All rights reserved.
PY - 2019
Y1 - 2019
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85077979339&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077979339&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85077979339
T3 - 36th International Conference on Machine Learning, ICML 2019
SP - 7146
EP - 7155
BT - 36th International Conference on Machine Learning, ICML 2019
PB - International Machine Learning Society (IMLS)
T2 - 36th International Conference on Machine Learning, ICML 2019
Y2 - 9 June 2019 through 15 June 2019
ER -