Evgenii Chzhen, chercheur postdoctoral au sein de l'Équipe de Probabilités et Statistique du Laboratoire de Mathématiques d'Orsay (Université Paris-Saclay) dirigera la session de juin des Séminaires DATAIA sur la thématique : “Algorithmic fairness: regression under demographic parity constraint”.

The first part of the talk, will be focused on a general overview of algorithmic fairness. Even though we will mainly focus on so-called group fairness constraints and main approaches which are guided by those constraints, we will briefly discuss individual fairness as an appealing alternative to the group fairness.

The second part of the talk will be focussed on the regression under demographic parity constraint. Describing a connection of this setup with the problem of Wasserstein barycenters, we will propose a post-processing estimation procedure which enjoys statistical fairness and risk guarantees.

Finally, we will discuss the notion of risk/fairness trade-off in the problem of regression under the demographic parity constraint. In particular, we will propose a new unfairness measure, which allows to provide a sharp analytic description of this trade-off.

Cet exposé est basé sur des travaux réalisés en communs avec Ch. Denis, M Hebiri, L. Oneto, M. Pontil, et N. Schreuder.

Pour télécharger la présentation, cliquez ici. 

Pour aller plus loin : 

• https://papers.nips.cc/paper/2020/file/51cdbd2611e844ece5d80878eb770436-Supplemental.pdf
• https://arxiv.org/abs/2007.14265