On conditional parity as a notion of non-discrimination in machine learning
This work addresses fairness and bias issues in ML for researchers and practitioners, but it is incremental as it builds on and unifies prior notions.
The paper tackles the problem of defining non-discrimination in machine learning by proposing conditional parity as a general notion, showing that it encompasses several existing measures and is amenable to statistical analysis through randomization and kernel-based tests.
We identify conditional parity as a general notion of non-discrimination in machine learning. In fact, several recently proposed notions of non-discrimination, including a few counterfactual notions, are instances of conditional parity. We show that conditional parity is amenable to statistical analysis by studying randomization as a general mechanism for achieving conditional parity and a kernel-based test of conditional parity.