TCS+ Talk: Wednesday, June 10 — Aaron Roth (UPenn)
On Wednesday, June 10th at 1 PM Eastern Time (10 AM Pacific Time, 7 PM Central European Time, 5 PM UTC), Aaron Roth will talk about “Correctness Protection via Differential Privacy” (abstract below).
Please sign up on the online form if you wish to join the talk as a group.
For more information about the TCS+ online seminar series, please see the website.
False discovery is a growing problem in scientific research. Despite sophisticated statistical techniques for controlling the false discovery rate and related statistics designed to protect against spurious discoveries, there is significant evidence that many published scientific papers contain incorrect conclusions.
In this talk we consider the role that adaptivity has in this problem. A fundamental disconnect between the theorems that control false discovery rate and the practice of science is that the theorems assume a fixed collection of hypotheses to be tested, selected non-adaptively before the data is gathered, whereas science is by definition an adaptive process, in which data is shared and re-used, while hypotheses are generated after seeing the results of previous tests.
We note that false discovery cannot be prevented when a substantial number of adaptive queries are made to the data, and data is used naively — i.e. when queries are answered exactly with their empirical estimates on a given finite data set. However we show that remarkably, there is a different way to evaluate statistical queries on a data set that allows even an adaptive analyst to make exponentially many queries to the data set, while guaranteeing that with high probability, all of the conclusions he draws generalize to the underlying distribution. This technique counter-intuitively involves actively perturbing the answers given to the data analyst, using techniques developed for privacy preservation — but in our application, the perturbations are added entirely to increase the utility of the data.
Joint work with Cynthia Dwork, Vitaly Feldman, Moritz Hardt, Toniann Pitassi, and Omer Reingold.