**** Lien zoom: https://univ-artois-fr.zoom.us/j/93828206912 ****
Le prochain séminaire GDR RADIA aura lieu Jeudi 26 Mars à 11h
Il s’agira d’une intervention de Nicolas Schreuder (LIGM – CNRS)
Title: Fairness in machine learning: a study of the Demographic Parity constraint
Abstract: In various domains, statistical algorithms trained on personal data take pivotal decisions which influence our lives on a daily basis. An increasing number of studies show that a naive use of these algorithms in sensitive domains may lead to unfair and discriminating decisions, often inheriting or even amplifying biases present in data.
Among the existing frameworks for studying this issue, we adopt the group fairness paradigm, in which individuals are viewed as members of protected groups. After introducing this paradigm, I will present several approaches and results for classification and regression under the Demographic Parity constraint, a standard group-fairness criterion.
References:
– A minimax framework for quantifying risk-fairness trade-off in regression (with E. Chzhen), Ann. Statist. 50(4): 2416-2442 (2022). DOI: 10.1214/22-AOS2198;
– Fair learning with Wasserstein barycenters for non-decomposable performance measures (with S. Gaucher and E. Chzhen), AISTATS 2023.
Tous les détails sur le séminaire du GDR et les vidéos des précédents séminaires ici:
https://gdr-radia.cnrs.fr/seminaire/
———————————————————————
Desinscription: envoyez un message a: bull-ia-unsubscribe@gdria.fr