Mathematics of Deep Learning Seminar: Guillermo Saprio

Date & Time


Location

Virtual

Title: Creating ML that is blindly fair while avoiding unnecessary harm

Abstract: In this talk I will first describe how to design fair ML algorithms that while helping protecting groups, are not unnecessarily hurting other non-protected ones. This will be followed by an extension where the protected groups are not known, so we need to design fair ML algorithms when we are actually blind to the groups we are trying to protect.

Advancing Research in Basic Science and MathematicsSubscribe to Flatiron Institute announcements and other foundation updates