[Statlist] FDS Seminar talk with Christophe Giraud, Paris Saclay University - 2 December 2021, 16:15-​17:15 CEST

[Maurer Letizia]

We are pleased to announce and invite you to the next talk in our FDS seminar series

"An Approachability Perspective to Fair Online Learning“
by Christophe Giraud, Paris Saclay University

Date and Time: Thursday, 2 December 2021, 16:15-​17:15 CEST
Place: ETH Zurich, HG F 3

Abstract: Machine learning is ubiquitous in daily decisions and producing fair and non-​discriminatory predictions is a major societal concern. Various criteria of fairness have been proposed in the literature, and we will start with a short (biased!) tour on fairness concepts in machine learning. Many decision problems are of a sequential nature, and efforts are needed to better handle such settings. We consider a general setting of fair online learning with stochastic sensitive and non-​sensitive contexts. We propose a unified approach for fair learning in this adversarial setting, by interpreting this problem as an approachability problem. This point of view offers a generic way to produce algorithms and theoretical results. Adapting Blackwell’s approachability theory, we exhibit a general necessary and sufficient condition for some learning objectives to be compatible with some fairness constraints, and we characterize the optimal trade-​off between the two, when they are not compatible. joint work with E. Chzhen and G. Stoltz


Organisers: A. Bandeira, H. Bölcskei, P. Bühlmann, F. Yang


IMPORTANT INFORMATION:

Please take note of the Covid certificate and mask requirements for joining this lecture. Further details can be found here, https://ethz.ch/services/en/news-and-events/internal-news/archive/2021/09/covid-certificate-requirement-in-all-lectures.html.

Seminar website: https://math.ethz.ch/sfs/news-and-events/data-science-seminar.html




	[[alternative HTML version deleted]]