Regression under demographic parity constraints via unlabeled post-processing

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chzhen, Evgenii, Hebiri, Mohamed, Taturyan, Gayane
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910537056518144
author Chzhen, Evgenii
Hebiri, Mohamed
Taturyan, Gayane
author_facet Chzhen, Evgenii
Hebiri, Mohamed
Taturyan, Gayane
contents We address the problem of performing regression while ensuring demographic parity, even without access to sensitive attributes during inference. We present a general-purpose post-processing algorithm that, using accurate estimates of the regression function and a sensitive attribute predictor, generates predictions that meet the demographic parity constraint. Our method involves discretization and stochastic minimization of a smooth convex function. It is suitable for online post-processing and multi-class classification tasks only involving unlabeled data for the post-processing. Unlike prior methods, our approach is fully theory-driven. We require precise control over the gradient norm of the convex function, and thus, we rely on more advanced techniques than standard stochastic gradient descent. Our algorithm is backed by finite-sample analysis and post-processing bounds, with experimental results validating our theoretical findings.
format Preprint
id arxiv_https___arxiv_org_abs_2407_15453
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Regression under demographic parity constraints via unlabeled post-processing
Chzhen, Evgenii
Hebiri, Mohamed
Taturyan, Gayane
Machine Learning
Computers and Society
We address the problem of performing regression while ensuring demographic parity, even without access to sensitive attributes during inference. We present a general-purpose post-processing algorithm that, using accurate estimates of the regression function and a sensitive attribute predictor, generates predictions that meet the demographic parity constraint. Our method involves discretization and stochastic minimization of a smooth convex function. It is suitable for online post-processing and multi-class classification tasks only involving unlabeled data for the post-processing. Unlike prior methods, our approach is fully theory-driven. We require precise control over the gradient norm of the convex function, and thus, we rely on more advanced techniques than standard stochastic gradient descent. Our algorithm is backed by finite-sample analysis and post-processing bounds, with experimental results validating our theoretical findings.
title Regression under demographic parity constraints via unlabeled post-processing
topic Machine Learning
Computers and Society
url https://arxiv.org/abs/2407.15453