Fairness through awareness
Cynthia Dwork, Moritz Hardt, et al.
ITCS 2012
Misapplication of statistical data analysis is a common cause of spurious discoveries in scientific research. Existing approaches to ensuring the validity of inferences drawn from data assume a fixed procedure to be performed, selected before the data are examined. In common practice, however, data analysis is an intrinsically adaptive process, with new analyses generated on the basis of data exploration, as well as the results of previous analyses on the same data. We demonstrate a new approach for addressing the challenges of adaptivity based on insights from privacy-preserving data analysis. As an application, we show how to safely reuse a holdout data set many times to validate the results of adaptively chosen analyses.
Cynthia Dwork, Moritz Hardt, et al.
ITCS 2012
Moritz Hardt, Aaron Roth
STOC 2012
Cynthia Dwork, Maurice Herlihy, et al.
STOC 1993
Danny Dolev, Cynthia Dwork, et al.
SIAM Journal on Computing