On Tradeoffs Between Fairness, Robustness, and Privacy Through Tilted Losses

Lead Student Presenter(s)

Jhih-Yi Hsieh

Abstract or Description

Fairness, robustness, and privacy are topics of concern for a wide range of applications in machine learning (ML). While prior works have focused on one or two of these aspects, the trade-offs between all three tight-knit aspects are underexplored. In this thesis, we investigate the connections between three metrics---fairness in terms of representation disparity, robustness to malicious training samples, and differential privacy, under a unified framework based on exponential tilting. More specifically, we propose a private training algorithm to optimize tilted losses proposed in prior literature, that characterizes robustness/fairness trade-offs. On a set of convex and non-convex models, our empirical results suggest that differential privacy is at odds with the benefits of tilting (i.e., promoting fairness or robustness). We also demonstrate that there is a tradeoff between the effectiveness of tilting and the cost of privacy noise.

Mentor

Virginia Smith