Algorithm Design: A Fairness-Accuracy Frontier

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liang, Annie, Lu, Jay, Mu, Xiaosheng, Okumura, Kyohei
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929337852231680
author Liang, Annie
Lu, Jay
Mu, Xiaosheng
Okumura, Kyohei
author_facet Liang, Annie
Lu, Jay
Mu, Xiaosheng
Okumura, Kyohei
contents Algorithm designers increasingly optimize not only for accuracy, but also for the fairness of the algorithm across pre-defined groups. We study the tradeoff between fairness and accuracy for any given set of inputs to the algorithm. We propose and characterize a fairness-accuracy frontier, which consists of the optimal points 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.
format Preprint
id arxiv_https___arxiv_org_abs_2112_09975
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Algorithm Design: A Fairness-Accuracy Frontier
Liang, Annie
Lu, Jay
Mu, Xiaosheng
Okumura, Kyohei
Theoretical Economics
Algorithm designers increasingly optimize not only for accuracy, but also for the fairness of the algorithm across pre-defined groups. We study the tradeoff between fairness and accuracy for any given set of inputs to the algorithm. We propose and characterize a fairness-accuracy frontier, which consists of the optimal points 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.
title Algorithm Design: A Fairness-Accuracy Frontier
topic Theoretical Economics
url https://arxiv.org/abs/2112.09975