Learning to be Fair: A Consequentialist Approach to Equitable Decision-Making

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chohlas-Wood, Alex, Coots, Madison, Zhu, Henry, Brunskill, Emma, Goel, Sharad
Format: Preprint
Veröffentlicht: 2021
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909103606988800
author Chohlas-Wood, Alex
Coots, Madison
Zhu, Henry
Brunskill, Emma
Goel, Sharad
author_facet Chohlas-Wood, Alex
Coots, Madison
Zhu, Henry
Brunskill, Emma
Goel, Sharad
contents In an attempt to make algorithms fair, the machine learning literature has largely focused on equalizing decisions, outcomes, or error rates across race or gender groups. To illustrate, consider a hypothetical government rideshare program that provides transportation assistance to low-income people with upcoming court dates. Following this literature, one might allocate rides to those with the highest estimated treatment effect per dollar, while constraining spending to be equal across race groups. That approach, however, ignores the downstream consequences of such constraints, and, as a result, can induce unexpected harms. For instance, if one demographic group lives farther from court, enforcing equal spending would necessarily mean fewer total rides provided, and potentially more people penalized for missing court. Here we present an alternative framework for designing equitable algorithms that foregrounds the consequences of decisions. In our approach, one first elicits stakeholder preferences over the space of possible decisions and the resulting outcomes--such as preferences for balancing spending parity against court appearance rates. We then optimize over the space of decision policies, making trade-offs in a way that maximizes the elicited utility. To do so, we develop an algorithm for efficiently learning these optimal policies from data for a large family of expressive utility functions. In particular, we use a contextual bandit algorithm to explore the space of policies while solving a convex optimization problem at each step to estimate the best policy based on the available information. This consequentialist paradigm facilitates a more holistic approach to equitable decision-making.
format Preprint
id arxiv_https___arxiv_org_abs_2109_08792
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Learning to be Fair: A Consequentialist Approach to Equitable Decision-Making
Chohlas-Wood, Alex
Coots, Madison
Zhu, Henry
Brunskill, Emma
Goel, Sharad
Machine Learning
Computers and Society
In an attempt to make algorithms fair, the machine learning literature has largely focused on equalizing decisions, outcomes, or error rates across race or gender groups. To illustrate, consider a hypothetical government rideshare program that provides transportation assistance to low-income people with upcoming court dates. Following this literature, one might allocate rides to those with the highest estimated treatment effect per dollar, while constraining spending to be equal across race groups. That approach, however, ignores the downstream consequences of such constraints, and, as a result, can induce unexpected harms. For instance, if one demographic group lives farther from court, enforcing equal spending would necessarily mean fewer total rides provided, and potentially more people penalized for missing court. Here we present an alternative framework for designing equitable algorithms that foregrounds the consequences of decisions. In our approach, one first elicits stakeholder preferences over the space of possible decisions and the resulting outcomes--such as preferences for balancing spending parity against court appearance rates. We then optimize over the space of decision policies, making trade-offs in a way that maximizes the elicited utility. To do so, we develop an algorithm for efficiently learning these optimal policies from data for a large family of expressive utility functions. In particular, we use a contextual bandit algorithm to explore the space of policies while solving a convex optimization problem at each step to estimate the best policy based on the available information. This consequentialist paradigm facilitates a more holistic approach to equitable decision-making.
title Learning to be Fair: A Consequentialist Approach to Equitable Decision-Making
topic Machine Learning
Computers and Society
url https://arxiv.org/abs/2109.08792