A minimax distortion view of differentially private query release

Weina Wang, Lei Ying, Junshan Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

We devise query-set independent mechanisms for the problem of differentially private query release. Specifically, a differentially private mechanism is constructed to publish a synthetic database, and "customized" companion estimators are then derived to provide the best possible answers. Accordingly, the distortion corresponding to the best mechanism at the worst- case query, named the minimax distortion, provides a fundamental characterization. For the general class of statistical queries, by deriving asymptotically sharp upper and lower bounds, we prove that the minimax distortion is O(1/n) as the database size n goes to infinity, with the squared-error distortion measure and fixed dimension of data entries.

Original languageEnglish (US)
Title of host publicationConference Record - Asilomar Conference on Signals, Systems and Computers
PublisherIEEE Computer Society
Pages1046-1050
Number of pages5
Volume2016-February
ISBN (Print)9781467385763
DOIs
StatePublished - Feb 26 2016
Event49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015 - Pacific Grove, United States
Duration: Nov 8 2015Nov 11 2015

Other

Other49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015
CountryUnited States
CityPacific Grove
Period11/8/1511/11/15

Fingerprint

Data acquisition

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Cite this

Wang, W., Ying, L., & Zhang, J. (2016). A minimax distortion view of differentially private query release. In Conference Record - Asilomar Conference on Signals, Systems and Computers (Vol. 2016-February, pp. 1046-1050). [7421298] IEEE Computer Society. https://doi.org/10.1109/ACSSC.2015.7421298

A minimax distortion view of differentially private query release. / Wang, Weina; Ying, Lei; Zhang, Junshan.

Conference Record - Asilomar Conference on Signals, Systems and Computers. Vol. 2016-February IEEE Computer Society, 2016. p. 1046-1050 7421298.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, W, Ying, L & Zhang, J 2016, A minimax distortion view of differentially private query release. in Conference Record - Asilomar Conference on Signals, Systems and Computers. vol. 2016-February, 7421298, IEEE Computer Society, pp. 1046-1050, 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015, Pacific Grove, United States, 11/8/15. https://doi.org/10.1109/ACSSC.2015.7421298
Wang W, Ying L, Zhang J. A minimax distortion view of differentially private query release. In Conference Record - Asilomar Conference on Signals, Systems and Computers. Vol. 2016-February. IEEE Computer Society. 2016. p. 1046-1050. 7421298 https://doi.org/10.1109/ACSSC.2015.7421298
Wang, Weina ; Ying, Lei ; Zhang, Junshan. / A minimax distortion view of differentially private query release. Conference Record - Asilomar Conference on Signals, Systems and Computers. Vol. 2016-February IEEE Computer Society, 2016. pp. 1046-1050
@inproceedings{0c3f42e21fe84728be76974687605ec3,
title = "A minimax distortion view of differentially private query release",
abstract = "We devise query-set independent mechanisms for the problem of differentially private query release. Specifically, a differentially private mechanism is constructed to publish a synthetic database, and {"}customized{"} companion estimators are then derived to provide the best possible answers. Accordingly, the distortion corresponding to the best mechanism at the worst- case query, named the minimax distortion, provides a fundamental characterization. For the general class of statistical queries, by deriving asymptotically sharp upper and lower bounds, we prove that the minimax distortion is O(1/n) as the database size n goes to infinity, with the squared-error distortion measure and fixed dimension of data entries.",
author = "Weina Wang and Lei Ying and Junshan Zhang",
year = "2016",
month = "2",
day = "26",
doi = "10.1109/ACSSC.2015.7421298",
language = "English (US)",
isbn = "9781467385763",
volume = "2016-February",
pages = "1046--1050",
booktitle = "Conference Record - Asilomar Conference on Signals, Systems and Computers",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - A minimax distortion view of differentially private query release

AU - Wang, Weina

AU - Ying, Lei

AU - Zhang, Junshan

PY - 2016/2/26

Y1 - 2016/2/26

N2 - We devise query-set independent mechanisms for the problem of differentially private query release. Specifically, a differentially private mechanism is constructed to publish a synthetic database, and "customized" companion estimators are then derived to provide the best possible answers. Accordingly, the distortion corresponding to the best mechanism at the worst- case query, named the minimax distortion, provides a fundamental characterization. For the general class of statistical queries, by deriving asymptotically sharp upper and lower bounds, we prove that the minimax distortion is O(1/n) as the database size n goes to infinity, with the squared-error distortion measure and fixed dimension of data entries.

AB - We devise query-set independent mechanisms for the problem of differentially private query release. Specifically, a differentially private mechanism is constructed to publish a synthetic database, and "customized" companion estimators are then derived to provide the best possible answers. Accordingly, the distortion corresponding to the best mechanism at the worst- case query, named the minimax distortion, provides a fundamental characterization. For the general class of statistical queries, by deriving asymptotically sharp upper and lower bounds, we prove that the minimax distortion is O(1/n) as the database size n goes to infinity, with the squared-error distortion measure and fixed dimension of data entries.

UR - http://www.scopus.com/inward/record.url?scp=84969776444&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969776444&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2015.7421298

DO - 10.1109/ACSSC.2015.7421298

M3 - Conference contribution

SN - 9781467385763

VL - 2016-February

SP - 1046

EP - 1050

BT - Conference Record - Asilomar Conference on Signals, Systems and Computers

PB - IEEE Computer Society

ER -