Timezone: »

 
Poster
Differentially Private Quantiles
Jennifer Gillenwater · Matthew Joseph · Alex Kulesza

Thu Jul 22 09:00 AM -- 11:00 AM (PDT) @
in Poster Session 5 »
Quantiles are often used for summarizing and understanding data. If that data is sensitive, it may be necessary to compute quantiles in a way that is differentially private, providing theoretical guarantees that the result does not reveal private information. However, when multiple quantiles are needed, existing differentially private algorithms fare poorly: they either compute quantiles individually, splitting the privacy budget, or summarize the entire distribution, wasting effort. In either case the result is reduced accuracy. In this work we propose an instance of the exponential mechanism that simultaneously estimates exactly $m$ quantiles from $n$ data points while guaranteeing differential privacy. The utility function is carefully structured to allow for an efficient implementation that returns estimates of all $m$ quantiles in time $O(mn\log(n) + m^2n)$. Experiments show that our method significantly outperforms the current state of the art on both real and synthetic data while remaining efficient enough to be practical.
Keywords: Learning Theory · Privacy, Anonymity, and Security · Social Aspects of Machine Learning

Author Information

Jennifer Gillenwater (Google Research NYC)
Matthew Joseph (Google)
Alex Kulesza (Google)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors