Maximin Relative Improvement: Fair Learning as a Bargaining Problem

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Han, Jiwoo, Banerjee, Moulinath, Sun, Yuekai
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914304977010688
author Han, Jiwoo
Banerjee, Moulinath
Sun, Yuekai
author_facet Han, Jiwoo
Banerjee, Moulinath
Sun, Yuekai
contents When deploying a single predictor across multiple subpopulations, we propose a fundamentally different approach: interpreting group fairness as a bargaining problem among subpopulations. This game-theoretic perspective reveals that existing robust optimization methods such as minimizing worst-group loss or regret correspond to classical bargaining solutions and embody different fairness principles. We propose relative improvement, the ratio of actual risk reduction to potential reduction from a baseline predictor, which recovers the Kalai-Smorodinsky solution. Unlike absolute-scale methods that may not be comparable when groups have different potential predictability, relative improvement provides axiomatic justification including scale invariance and individual monotonicity. We establish finite-sample convergence guarantees under mild conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2602_04155
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Maximin Relative Improvement: Fair Learning as a Bargaining Problem
Han, Jiwoo
Banerjee, Moulinath
Sun, Yuekai
Machine Learning
Computer Science and Game Theory
When deploying a single predictor across multiple subpopulations, we propose a fundamentally different approach: interpreting group fairness as a bargaining problem among subpopulations. This game-theoretic perspective reveals that existing robust optimization methods such as minimizing worst-group loss or regret correspond to classical bargaining solutions and embody different fairness principles. We propose relative improvement, the ratio of actual risk reduction to potential reduction from a baseline predictor, which recovers the Kalai-Smorodinsky solution. Unlike absolute-scale methods that may not be comparable when groups have different potential predictability, relative improvement provides axiomatic justification including scale invariance and individual monotonicity. We establish finite-sample convergence guarantees under mild conditions.
title Maximin Relative Improvement: Fair Learning as a Bargaining Problem
topic Machine Learning
Computer Science and Game Theory
url https://arxiv.org/abs/2602.04155