A Maximal Correlation Framework for Fair Machine Learning

As machine learning algorithms grow in popularity and diversify to many industries, ethical and legal concerns regarding their fairness have become increasingly relevant. We explore the problem of algorithmic fairness, taking an information–theoretic view. The maximal correlation framework is introd...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Joshua Lee, Yuheng Bu, Prasanna Sattigeri, Rameswar Panda, Gregory W. Wornell, Leonid Karlinsky, Rogerio Schmidt Feris
Format:	Artigo
Jezik:	Inglês
Izdano:	MDPI AG 2022-03-01
Serija:	Entropy
Teme:	fairness HGR maximal correlation independence criterion separation criterion
Online dostop:	https://www.mdpi.com/1099-4300/24/4/461
Oznake:	Označite Brez oznak, prvi označite!