Year: 2017
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Ritov, Ya'acov, Sun, Yuekai, Zhao, Ruofei
Institution: University of Michigan
Language: English
Subfield: Safety Research
Field: Social Sciences
Domain: Social Sciences
SDG: Reduced inequalities
Open Access status: green
OpenAlex ID: W2676656730