We explore the following question: Is a decision-making program fair, for some useful definition of fairness? First, we describe how several algorithmic fairness questions can be phrased as program verification problems. Second, we discuss an automated verification technique for proving or disproving fairness of decision-making programs with respect to a probabilistic model of the population.
@article{arxiv.1610.06067,
title = {Fairness as a Program Property},
author = {Aws Albarghouthi and Loris D'Antoni and Samuel Drews and Aditya Nori},
journal= {arXiv preprint arXiv:1610.06067},
year = {2016}
}