Cynthia
Dwork
Microsoft
Research
Lipschitz
Mappings,
Differential
Privacy,
and
Fairness
Through
Awareness
We present a framework for fair classification comprising (1) a (hypothetical) task-specific metric for determining the degree to which individuals are similar with respect to the classification task at hand; (2) an algorithm for maximizing utility subject to the fairness constraint that similar individuals are treated similarly; and (3) an adaptation for achieving the complementary goal of "fair affirmative action," which guarantees statistical parity (the demographics of the set of individuals receiving any classification are the same as the demographics of the underlying population), while treating similar individuals as similarly as possible.
Our approach, which handles arbitrary classifiers, with arbitrary utilities, provides a (theoretical) method by which an on-line advertising network can prevent discrimination against protected groups, even when the advertisers are unknown and untrusted. We also establish a connection to differential privacy, where similar databases give rise to similar output distributions.
This work is joint with Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard Zemel.
Biography: Cynthia Dwork, Distinguished Scientist at Microsoft Research, is the world's foremost expert on placing privacy-preserving data analysis on a mathematically rigorous foundation. A cornerstone of this work is differential privacy, a strong privacy guarantee frequently permitting highly accurate data analysis. Dr. Dwork has also made seminal contributions in cryptography and distributed computing, and is a recipient of the Edsger W. Dijkstra Prize, recognizing some of her earliest work establishing the pillars on which every fault-tolerant system has been built for decades. She is a member of the US National Academy of Engineering and a Fellow of the American Academy of Arts and Sciences.