Timezone: »

 
Poster
A Unified Approach to Fair Online Learning via Blackwell Approachability
Evgenii Chzhen · Christophe Giraud · Gilles Stoltz

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @
in Poster Session 6 »

We provide a setting and a general approach to fair online learning with stochastic sensitive and non-sensitive contexts.The setting is a repeated game between the Player and Nature, where at each stage both pick actions based on the contexts. Inspired by the notion of unawareness, we assume that the Player can only access the non-sensitive context before making a decision, while we discuss both cases of Nature accessing the sensitive contexts and Nature unaware of the sensitive contexts. Adapting Blackwell's approachability theory to handle the case of an unknown contexts' distribution, we provide a general necessary and sufficient condition for learning objectives to be compatible with some fairness constraints. This condition is instantiated on (group-wise) no-regret and (group-wise) calibration objectives, and on demographic parity as an additional constraint. When the objective is not compatible with the constraint, the provided framework permits to characterise the optimal trade-off between the two.

Keywords: Theory · Machine Learning · Graph Learning · Online Learning · Fairness

Author Information

Evgenii Chzhen (Université Paris-Saclay, CNRS)
Christophe Giraud (Université Paris Saclay)
Gilles Stoltz (HEC Paris)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors