| _version_ |
1826190261158412288
|
| collection |
MIT
|
| description |
© 2019 Neural information processing systems foundation. All rights reserved. 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.
|
| first_indexed |
2024-09-23T08:37:32Z
|
| format |
Article
|
| id |
mit-1721.1/137380
|
| institution |
Massachusetts Institute of Technology
|
| language |
English
|
| last_indexed |
2024-09-23T08:37:32Z
|
| publishDate |
2021
|
| record_format |
dspace
|
| spelling |
mit-1721.1/1373802021-11-05T03:39:28Z Private testing of distributions via sample permutations © 2019 Neural information processing systems foundation. All rights reserved. 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. 2021-11-04T17:42:54Z 2021-11-04T17:42:54Z 2019-12 2021-03-26T14:05:00Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/137380 2019. "Private testing of distributions via sample permutations." Advances in Neural Information Processing Systems, 32. en https://papers.nips.cc/paper/2019/hash/8e036cc193d0af59aa9b22821248292b-Abstract.html Advances in Neural Information Processing Systems Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Neural Information Processing Systems (NIPS)
|
| spellingShingle |
Private testing of distributions via sample permutations
|
| title |
Private testing of distributions via sample permutations
|
| title_full |
Private testing of distributions via sample permutations
|
| title_fullStr |
Private testing of distributions via sample permutations
|
| title_full_unstemmed |
Private testing of distributions via sample permutations
|
| title_short |
Private testing of distributions via sample permutations
|
| title_sort |
private testing of distributions via sample permutations
|
| url |
https://hdl.handle.net/1721.1/137380
|