f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization

arXiv:2312.03259v2 Announce Type: replace
Abstract: Training and deploying machine learning models that meet fairness criteria for protected groups are fundamental in modern artificial intelligence. While numerous constraints and regularization terms have been proposed in the literature to promote fairness in machine learning tasks, most of these methods are not amenable to stochastic optimization due to the complex and nonlinear structure of constraints and regularizers. Here, the term "stochastic" refers to the ability of the algorithm to work with small mini-batches …

abstract artificial artificial intelligence arxiv constraints cs.lg fair fairness framework intelligence literature machine machine learning machine learning models modern promote regularization risk robust scalable tasks terms training type