TY - JOUR
T1 - Private testing of distributions via sample permutations
AU - Aliakbarpour, Maryam
AU - Diakonikolas, Ilias
AU - Kane, Daniel
AU - Rubinfeld, Ronitt
N1 - Publisher Copyright:
© 2019 Neural information processing systems foundation. All rights reserved.
PY - 2019
Y1 - 2019
N2 - Statistical tests are at the heart of many scientific tasks. To validate their hypotheses, researchers in medical and social sciences use individuals' data. The sensitivity of participants' data requires the design of statistical tests that ensure the privacy of the individuals in the most efficient way. In this paper, we use the framework of property testing to design algorithms to test the properties of the distribution that the data is drawn from with respect to differential privacy. In particular, we investigate testing two fundamental properties of distributions: (1) testing the equivalence of two distributions when we have unequal numbers of samples from the two distributions. (2) Testing independence of two random variables. In both cases, we show that our testers achieve near optimal sample complexity (up to logarithmic factors). Moreover, our dependence on the privacy parameter is an additive term, which indicates that differential privacy can be obtained in most regimes of parameters for free.
AB - Statistical tests are at the heart of many scientific tasks. To validate their hypotheses, researchers in medical and social sciences use individuals' data. The sensitivity of participants' data requires the design of statistical tests that ensure the privacy of the individuals in the most efficient way. In this paper, we use the framework of property testing to design algorithms to test the properties of the distribution that the data is drawn from with respect to differential privacy. In particular, we investigate testing two fundamental properties of distributions: (1) testing the equivalence of two distributions when we have unequal numbers of samples from the two distributions. (2) Testing independence of two random variables. In both cases, we show that our testers achieve near optimal sample complexity (up to logarithmic factors). Moreover, our dependence on the privacy parameter is an additive term, which indicates that differential privacy can be obtained in most regimes of parameters for free.
UR - http://www.scopus.com/inward/record.url?scp=85078026429&partnerID=8YFLogxK
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.conferencearticle???
AN - SCOPUS:85078026429
VL - 32
JO - Advances in Neural Information Processing Systems
JF - Advances in Neural Information Processing Systems
SN - 1049-5258
Y2 - 8 December 2019 through 14 December 2019
ER -