BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:What Can Fair ML Learn from Economic Theories of Distributive Just
 ice? - Hoda Heidari\, ETH Zurich 
DTSTART:20190116T130000Z
DTEND:20190116T140000Z
UID:TALK116905@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Recently\, a number of technical solutions have been proposed 
 for tackling algorithmic unfairness and discrimination. I will talk about 
 some of the connections between these proposals and to the long-establishe
 d economic theories of fairness and distributive justice. In particular\, 
 I will overview the axiomatic characterization of measures of (income) ine
 quality\, and present them as a unifying framework for quantifying individ
 ual- and group-level unfairness\; I will propose the use of cardinal socia
 l welfare functions as an effective method for bounding individual-level i
 nequality\; and last but not least\, I will cast existing notions of algor
 ithmic (un)fairness as special cases of economic models of equality of opp
 ortunity---through this lens\, I hope to offer a better understanding of t
 he moral assumptions underlying technical definitions of fairness.
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR