Meta Optimality for Demographic Parity Constrained Regression via Post-Processing

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Fukuchi, Kazuto
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909650334515200
author Fukuchi, Kazuto
author_facet Fukuchi, Kazuto
contents We address the regression problem under the constraint of demographic parity, a commonly used fairness definition. Recent studies have revealed fair minimax optimal regression algorithms, the most accurate algorithms that adhere to the fairness constraint. However, these analyses are tightly coupled with specific data generation models. In this paper, we provide meta-theorems that can be applied to various situations to validate the fair minimax optimality of the corresponding regression algorithms. Furthermore, we demonstrate that fair minimax optimal regression can be achieved through post-processing methods, allowing researchers and practitioners to focus on improving conventional regression techniques, which can then be efficiently adapted for fair regression.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13947
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Meta Optimality for Demographic Parity Constrained Regression via Post-Processing
Fukuchi, Kazuto
Machine Learning
We address the regression problem under the constraint of demographic parity, a commonly used fairness definition. Recent studies have revealed fair minimax optimal regression algorithms, the most accurate algorithms that adhere to the fairness constraint. However, these analyses are tightly coupled with specific data generation models. In this paper, we provide meta-theorems that can be applied to various situations to validate the fair minimax optimality of the corresponding regression algorithms. Furthermore, we demonstrate that fair minimax optimal regression can be achieved through post-processing methods, allowing researchers and practitioners to focus on improving conventional regression techniques, which can then be efficiently adapted for fair regression.
title Meta Optimality for Demographic Parity Constrained Regression via Post-Processing
topic Machine Learning
url https://arxiv.org/abs/2506.13947