Theory-Experimental Seminar

Annie Liang

Northwestern University


webinar – 14:30


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.

Download pdf
Leave Comment

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>

clear formSubmit

This site uses Akismet to reduce spam. Learn how your comment data is processed.