Locally Private Hypothesis Testing

Or Sheffet
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:4605-4614, 2018.

Abstract

We initiate the study of differentially private hypothesis testing in the local-model, under both the standard (symmetric) randomized-response mechanism (Warner 1965, Kasiviswanathan et al, 2008) and the newer (non-symmetric) mechanisms (Bassily & Smith, 2015, Bassily et al, 2017). First, we study the general framework of mapping each user’s type into a signal and show that the problem of finding the maximum-likelihood distribution over the signals is feasible. Then we discuss the randomized-response mechanism and show that, in essence, it maps the null- and alternative-hypotheses onto new sets, an affine translation of the original sets. We then give sample complexity bounds for identity and independence testing under randomized-response. We then move to the newer non-symmetric mechanisms and show that there too the problem of finding the maximum-likelihood distribution is feasible. Under the mechanism of Bassily et al we give identity and independence testers with better sample complexity than the testers in the symmetric case, and we also propose a $\chi^2$-based identity tester which we investigate empirically.

Cite this Paper


BibTeX
@InProceedings{pmlr-v80-sheffet18a, title = {Locally Private Hypothesis Testing}, author = {Sheffet, Or}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {4605--4614}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/sheffet18a/sheffet18a.pdf}, url = {http://proceedings.mlr.press/v80/sheffet18a.html}, abstract = {We initiate the study of differentially private hypothesis testing in the local-model, under both the standard (symmetric) randomized-response mechanism (Warner 1965, Kasiviswanathan et al, 2008) and the newer (non-symmetric) mechanisms (Bassily & Smith, 2015, Bassily et al, 2017). First, we study the general framework of mapping each user’s type into a signal and show that the problem of finding the maximum-likelihood distribution over the signals is feasible. Then we discuss the randomized-response mechanism and show that, in essence, it maps the null- and alternative-hypotheses onto new sets, an affine translation of the original sets. We then give sample complexity bounds for identity and independence testing under randomized-response. We then move to the newer non-symmetric mechanisms and show that there too the problem of finding the maximum-likelihood distribution is feasible. Under the mechanism of Bassily et al we give identity and independence testers with better sample complexity than the testers in the symmetric case, and we also propose a $\chi^2$-based identity tester which we investigate empirically.} }
Endnote
%0 Conference Paper %T Locally Private Hypothesis Testing %A Or Sheffet %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-sheffet18a %I PMLR %P 4605--4614 %U http://proceedings.mlr.press/v80/sheffet18a.html %V 80 %X We initiate the study of differentially private hypothesis testing in the local-model, under both the standard (symmetric) randomized-response mechanism (Warner 1965, Kasiviswanathan et al, 2008) and the newer (non-symmetric) mechanisms (Bassily & Smith, 2015, Bassily et al, 2017). First, we study the general framework of mapping each user’s type into a signal and show that the problem of finding the maximum-likelihood distribution over the signals is feasible. Then we discuss the randomized-response mechanism and show that, in essence, it maps the null- and alternative-hypotheses onto new sets, an affine translation of the original sets. We then give sample complexity bounds for identity and independence testing under randomized-response. We then move to the newer non-symmetric mechanisms and show that there too the problem of finding the maximum-likelihood distribution is feasible. Under the mechanism of Bassily et al we give identity and independence testers with better sample complexity than the testers in the symmetric case, and we also propose a $\chi^2$-based identity tester which we investigate empirically.
APA
Sheffet, O.. (2018). Locally Private Hypothesis Testing. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:4605-4614 Available from http://proceedings.mlr.press/v80/sheffet18a.html.

Related Material