Statistical Approximating Distributions Under Differential Privacy
Statistics computed from data are viewed as random variables. When they are used for tasks like hypothesis testing and confidence intervals, their true finite sample distributions are often replaced by approximating distributions that are easier to work with (for example, the Gaussian, which results...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Labor Dynamics Institute
2018-12-01
|
| Series: | The Journal of Privacy and Confidentiality |
| Subjects: | |
| Online Access: | https://journalprivacyconfidentiality.org/index.php/jpc/article/view/666 |
| _version_ | 1818471635464749056 |
|---|---|
| author | Yue Wang Daniel Kifer Jaewoo Lee Vishesh Karwa |
| author_facet | Yue Wang Daniel Kifer Jaewoo Lee Vishesh Karwa |
| author_sort | Yue Wang |
| collection | DOAJ |
| description | Statistics computed from data are viewed as random variables. When they are used for tasks like hypothesis testing and confidence intervals, their true finite sample distributions are often replaced by approximating distributions that are easier to work with (for example, the Gaussian, which results from using approximations justified by the Central Limit Theorem). When data are perturbed by differential privacy, the approximating distributions also need to be modified. Prior work provided various competing methods for creating such approximating distributions with little formal justification beyond the fact that they worked well empirically.
In this paper, we study the question of how to generate statistical approximating distributions for differentially private statistics, provide finite sample guarantees for the quality of the approximations. |
| first_indexed | 2024-04-14T03:54:03Z |
| format | Article |
| id | doaj.art-09c3d98f749f4385a3dcefbde6db6f07 |
| institution | Directory Open Access Journal |
| issn | 2575-8527 |
| language | English |
| last_indexed | 2024-04-14T03:54:03Z |
| publishDate | 2018-12-01 |
| publisher | Labor Dynamics Institute |
| record_format | Article |
| series | The Journal of Privacy and Confidentiality |
| spelling | doaj.art-09c3d98f749f4385a3dcefbde6db6f072022-12-22T02:13:52ZengLabor Dynamics InstituteThe Journal of Privacy and Confidentiality2575-85272018-12-018110.29012/jpc.666Statistical Approximating Distributions Under Differential PrivacyYue Wang0Daniel Kifer1Jaewoo Lee2Vishesh Karwa3Penn StatePenn StateUniversity of GeorgiaFox School of Business; Temple UniversityStatistics computed from data are viewed as random variables. When they are used for tasks like hypothesis testing and confidence intervals, their true finite sample distributions are often replaced by approximating distributions that are easier to work with (for example, the Gaussian, which results from using approximations justified by the Central Limit Theorem). When data are perturbed by differential privacy, the approximating distributions also need to be modified. Prior work provided various competing methods for creating such approximating distributions with little formal justification beyond the fact that they worked well empirically. In this paper, we study the question of how to generate statistical approximating distributions for differentially private statistics, provide finite sample guarantees for the quality of the approximations.https://journalprivacyconfidentiality.org/index.php/jpc/article/view/666Differential PrivacyApproximating DistributionsFinite Sample Guarantees |
| spellingShingle | Yue Wang Daniel Kifer Jaewoo Lee Vishesh Karwa Statistical Approximating Distributions Under Differential Privacy The Journal of Privacy and Confidentiality Differential Privacy Approximating Distributions Finite Sample Guarantees |
| title | Statistical Approximating Distributions Under Differential Privacy |
| title_full | Statistical Approximating Distributions Under Differential Privacy |
| title_fullStr | Statistical Approximating Distributions Under Differential Privacy |
| title_full_unstemmed | Statistical Approximating Distributions Under Differential Privacy |
| title_short | Statistical Approximating Distributions Under Differential Privacy |
| title_sort | statistical approximating distributions under differential privacy |
| topic | Differential Privacy Approximating Distributions Finite Sample Guarantees |
| url | https://journalprivacyconfidentiality.org/index.php/jpc/article/view/666 |
| work_keys_str_mv | AT yuewang statisticalapproximatingdistributionsunderdifferentialprivacy AT danielkifer statisticalapproximatingdistributionsunderdifferentialprivacy AT jaewoolee statisticalapproximatingdistributionsunderdifferentialprivacy AT visheshkarwa statisticalapproximatingdistributionsunderdifferentialprivacy |