BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Out of Scope\, Out of Mind: Expanding Frontiers for Fairness Parad
 igms in ML - Serena Wang (UC Berkeley)
DTSTART:20220222T160000Z
DTEND:20220222T170000Z
UID:TALK169175@talks.cam.ac.uk
CONTACT:Artem Khovanov
DESCRIPTION:Much of the recent literature in machine learning (ML) fairnes
 s has focused on statistical group-based notions of fairness\, where the g
 oal is to achieve or equalize some model performance metric across protect
 ed groups. While this framework has received widespread mathematical atten
 tion\, this talk will discuss several of its practical and philosophical l
 imitations. First\, there is a practical issue of enforcing group-based fa
 irness constraints when the data on protected groups is incomplete or nois
 y. Second\, even with perfect data\, we discuss rule-based notions of fair
  treatment that group-based fairness notions still cannot philosophically 
 capture. Finally\, even the most heavily fairness-constrained ML model mig
 ht still fall short in satisfying societal needs due to choices in problem
  formulation and downstream interventions. Thus\, we argue that the typica
 l view of the ML life cycle in ML research needs to be expanded to capture
  a full spectrum of societal impacts.
LOCATION:Castlereagh Room\, Fisher Building\, St Johns College\, Cambridge
 \, CB2 1TP
END:VEVENT
END:VCALENDAR