Statistical learning for constrained functional parameters in infinite-dimensional models with applications in fair machine learning

arXiv:2404.09847v1 Announce Type: cross
Abstract: Constrained learning has become increasingly important, especially in the realm of algorithmic fairness and machine learning. In these settings, predictive models are developed specifically to satisfy pre-defined notions of fairness. Here, we study the general problem of constrained statistical machine learning through a statistical functional lens. We consider learning a function-valued parameter of interest under the constraint that one or several pre-specified real-valued functional parameters equal zero or are otherwise bounded. We characterize the constrained …

abstract algorithmic fairness applications arxiv become cs.cy cs.lg fair fairness functional general machine machine learning parameters predictive predictive models realm statistical stat.me stat.ml study type