Empirical Risk Minimization under Fairness Constraints

Efficient Policy Learning

We consider the problem of using observational data to learn treatment assignment policies that satisfy certain constraints specified by a practitioner, such as budget, fairness, or functional form constraints. This problem has previously been studied in economics, statistics, and computer science, and several regret-consistent methods have been proposed. However, several key analytical compone...

Fairness-Aware Learning with Restriction of Universal Dependency using f-Divergences

Fairness-aware learning is a novel framework for classification tasks. Like regular empirical risk minimization (ERM), it aims to learn a classifier with a low error rate, and at the same time, for the predictions of the classifier to be independent of sensitive features, such as gender, religion, race, and ethnicity. Existing methods can achieve low dependencies on given samples, but this is n...

Expanded HTA: Enhancing Fairness and Legitimacy

All societies face the need to make judgments about what interventions (both public health and personal medical) to provide to their populations under reasonable resource constraints. Their decisions should be informed by good evidence and arguments from health technology assessment (HTA). But if HTA restricts itself to evaluations of safety, efficacy, and cost-effectiveness, it risks being vie...

PAT: Towards Flexible Verification under Fairness

Recent development on distributed systems has shown that a variety of fairness constraints (some of which are only recently defined) play vital roles in designing self-stabilizing population protocols. Current practice of system analysis is, however, deficient under fairness. In this work, we present PAT, a toolkit for flexible and efficient system analysis under fairness. A unified algorithm i...

A utility minimization approach for energy-aware cooperative content distribution with fairness constraints