Gultchin, Limor;
Guo, Siyuan;
Malek, Alan;
Chiappa, Silvia;
Silva, Ricardo;
(2024)
Pragmatic Fairness: Developing Policies with
Outcome Disparity Control.
In: Locatello, Francesco and Didelez, Vanessa, (eds.)
Proceedings of Machine Learning Research.
(pp. pp. 243-264).
PMLR: Los Angeles, California, USA.
Preview |
Text
gultchin24a.pdf - Published Version Download (941kB) | Preview |
Abstract
We introduce a causal framework for designing optimal policies that satisfy classes of fairness constraints. We take a pragmatic approach asking what we can do with an action space available from historical data, with no further experimentation and novel actions immediately available. We propose two different fairness constraints: a “moderation breaking’ constraint which aims at reducing disparity in outcome levels across sensitive attributes to the extent the provided action space permits; and an “equal benefit” constraint which aims at distributing gain from the new and maximized policy equally across sensitive attribute levels, and thus at keeping pre-existing preferential treatment in place or avoiding the introduction of new disparity. We introduce practical methods for implementing the constraints and illustrate their uses on experiments with semi-synthetic models.
Type: | Proceedings paper |
---|---|
Title: | Pragmatic Fairness: Developing Policies with Outcome Disparity Control |
Event: | 3rd Conference on Causal Learning and Reasoning |
Open access status: | An open access version is available from UCL Discovery |
Publisher version: | https://proceedings.mlr.press/v236/ |
Language: | English |
Additional information: | Creative Commons Attribution 4.0 International License, http://creativecommons.org/licenses/by/4.0/legalcode. |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science |
URI: | https://discovery.ucl.ac.uk/id/eprint/10193564 |




Archive Staff Only
![]() |
View Item |