Evgenii Chzhen (Université Paris-Saclay, France)

Demographic parity constraint for algorithmic fairness : a statistical perspective

Abstract. In this talk I will give a brief introduction to the recently emerged field of algorithmic fairness and advocate for a statistical study of the problem. To support my claims, I will focus on the Demographic Parity fairness constraint, describing various connections to classical statistical theory, optimal transport, and conformal prediction literature. In particular, we will study the form of an optimal prediction function under this constraint in both regression and classification. Then, I will describe a learning procedure which is supported by statistical guarantees under no or mild assumptions on the underlying data distribution.
This talk is based on a sequence of joint works with Ch. Denis, S. Gaucher, M. Hebiri, L. Oneto, M. Pontil, and N. Schreuder.