Timezone: »

 
Poster
Multicalibration: Calibration for the (Computationally-Identifiable) Masses
Ursula Hebert-Johnson · Michael Kim · Omer Reingold · Guy Rothblum

Thu Jul 12 09:15 AM -- 12:00 PM (PDT) @ Hall B #167

We develop and study multicalibration as a new measure of fairness in machine learning that aims to mitigate inadvertent or malicious discrimination that is introduced at training time (even from ground truth data). Multicalibration guarantees meaningful (calibrated) predictions for every subpopulation that can be identified within a specified class of computations. The specified class can be quite rich; in particular, it can contain many overlapping subgroups of a protected group. We demonstrate that in many settings this strong notion of protection from discrimination is provably attainable and aligned with the goal of obtaining accurate predictions. Along the way, we present algorithms for learning a multicalibrated predictor, study the computational complexity of this task, and illustrate tight connections to the agnostic learning model.

Author Information

Ursula Hebert-Johnson (Stanford University)
Michael Kim (Stanford University)
Omer Reingold (Stanford University)
Guy Rothblum (Weizmann Institute of Science)

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

More from the Same Authors