6 papers · 1 filter
Minimax Group Fairness in Strategic Classification
Emily Diana, Saeed Sharifi-Malvajerdi, Ali Vakilian
In strategic classification, agents manipulate their features, at a cost, to receive a positive classification outcome from the learner's classifier. The goal of the learner in suc…
Balanced Filtering via Disclosure-Controlled Proxies
Siqi Deng, Emily Diana, Michael Kearns +1
We study the problem of collecting a cohort or set that is balanced with respect to sensitive groups when group membership is unavailable or prohibited from use at deployment time.…
Multiaccurate Proxies for Downstream Fairness
Emily Diana, Wesley Gill, Michael Kearns +3
We study the problem of training a model that must obey demographic fairness conditions when the sensitive features are not available at training time -- in other words, how can we…
Lexicographically Fair Learning: Algorithms and Generalization
Emily Diana, Wesley Gill, Ira Globus-Harris +3
We extend the notion of minimax fairness in supervised learning problems to its natural conclusion: lexicographic minimax fairness (or lexifairness for short). Informally, given a…
Minimax Group Fairness: Algorithms and Experiments
Emily Diana, Wesley Gill, Michael Kearns +2
We consider a recently introduced framework in which fairness is measured by worst-case outcomes across groups, rather than by the more standard differences between group outcomes.…
Algorithms and Learning for Fair Portfolio Design
Emily Diana, Travis Dick, Hadi Elzayn +5
We consider a variation on the classical finance problem of optimal portfolio design. In our setting, a large population of consumers is drawn from some distribution over risk tole…