research
∙
09/08/2022
Black-Box Audits for Group Distribution Shifts
When a model informs decisions about people, distribution shifts can cre...
share
research
∙
02/18/2020
Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness
We turn the definition of individual fairness on its head—rather than as...
research
∙
06/27/2019
Learning Fair Representations for Kernel Models
Fair representations are a powerful tool for establishing criteria like ...
research
∙
06/21/2019
FlipTest: Fairness Auditing via Optimal Transport
We present FlipTest, a black-box auditing technique for uncovering subgr...
research
∙
10/16/2018
Hunting for Discriminatory Proxies in Linear Regression Models
A machine learning model may exhibit discrimination when used to make de...
research
∙
08/26/2018
Discriminative but Not Discriminatory: A Comparison of Fairness Definitions under Different Worldviews
We mathematically compare three competing definitions of group-level non...
research
∙
09/05/2017