Review of Mathematical frameworks for Fairness in Machine Learning - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2020

Review of Mathematical frameworks for Fairness in Machine Learning

Eustasio del Barrio
  • Fonction : Auteur
Paula Gordaliza
  • Fonction : Auteur

Résumé

A review of the main fairness definitions and fair learning methodologies proposed in the literature over the last years is presented from a mathematical point of view. Following our independence-based approach, we consider how to build fair algorithms and the consequences on the degradation of their performance compared to the possibly unfair case. This corresponds to the price for fairness given by the criteria $\textit{statistical parity}$ or $\textit{equality of odds}$. Novel results giving the expressions of the optimal fair classifier and the optimal fair predictor (under a linear regression gaussian model) in the sense of $\textit{equality of odds}$ are presented.

Dates et versions

hal-02964972 , version 1 (12-10-2020)

Identifiants

Citer

Eustasio del Barrio, Paula Gordaliza, Jean-Michel Loubes. Review of Mathematical frameworks for Fairness in Machine Learning. 2020. ⟨hal-02964972⟩
103 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More