Polynomial time auditing of statistical subgroup fairness for Gaussian data. (arXiv:2401.16439v1 [cs.LG])

We study the problem of auditing classifiers with the notion of statistical
subgroup fairness. Kearns et al. (2018) has shown that the problem of auditing
combinatorial subgroups fairness is as hard as agnostic learning. Essentially
all work on remedying statistical measures of discrimination against subgroups
assumes access to an oracle for this problem, despite the fact that no
efficient algorithms are known for it. If we assume the data distribution is
Gaussian, or even merely log-concave, then a recent line …

arxiv classifiers cs.lg data discrimination fairness notion polynomial statistical study subgroups work