Moritz Hardt, Raghu Meka, et al.
JMLR
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.
Moritz Hardt, Raghu Meka, et al.
JMLR
Moritz Hardt, Eric Price
NeurIPS 2014
Vitaly Feldman, David Xiao
SIAM Journal on Computing
Vitaly Feldman, Elena Grigorescu, et al.
Journal of the ACM