CS Theory Colloquium Series

Fall 2023

Monday, October 23rd, 3:30pm, Harold Frank Hall (HFH) room 1132

Speaker: Parikshit Gopalan (Apple)

Title: Loss Minimization and Multi-group Fairness

Abstract: Training a predictor to minimize a loss function fixed in advance is the dominant paradigm in machine learning. However, loss minimization by itself might not guarantee desiderata like fairness and accuracy that one could reasonably expect from a predictor. In contrast, various group-fairness notions have been proposed that constrain the predictor to share certain statistical properties of the data, even when conditioned on a rich family of subgroups. There is no explicit attempt at loss minimization.

In this talk, we will explore some recently discovered connections between loss minimization and notions of multi-group fairness. We will see settings where one can lead to the other, and other settings where this is unlikely.

Bio: Parikshit Gopalan is a machine learning researcher at Apple. His current interests center on fairness and trust in machine learning. In the past, he has made important contributions to erasure coding for distributed storage, coding theory and computational complexity. His work has been awarded the 2014 Joint IEEE Communication Society & Information Theory Society Paper Prize, the 2013 Microsoft TCN Storage Technical Award and the best paper award for the 2012 USENIX Advanced Technology Conference. In the past, he has been a researcher at VMware, Microsoft Research (Silicon valley and Redmond), a postdoc at the University of Washington and UT Austin, a graduate student at Georgia Tech and an undergraduate at IIT Bombay.