skip to main content

Ulric B. and Evelyn L. Bray Social Sciences Seminar

Wednesday, March 15, 2023
4:00pm to 5:00pm
Add to Cal
Baxter Lecture Hall
Algorithm Design: A Fairness-Accuracy Frontier
Annie Liang, Assistant Professor, Department of Economics, Northwestern University,

Abstract: Algorithm designers increasingly optimize not only for accuracy but also fairness, defined as how similar accuracy is across demographic groups. We study the tradeoff between fairness and accuracy via a fairness-accuracy frontier, which consists of the optimal points (for a fixed set of inputs) across a broad range of preferences over fairness and accuracy. Our results identify a simple property of the inputs, group-balance, which qualitatively determines the shape of the frontier. We further study an information-design problem where the designer flexibly regulates the inputs (e.g., by coarsening an input or banning its use) but the algorithm is chosen by another agent. Whether it is optimal to ban an input generally depends on the designer's preferences. But when inputs are group-balanced, then excluding group identity is strictly suboptimal for all designers, and when the designer has access to group identity, then it is strictly suboptimal to exclude any informative input.

For more information, please contact Barbara Estrada by phone at 626-395-4083 or by email at [email protected].