A minimax distortion view of differentially private query release

Weina Wang; Lei Ying; Junshan Zhang

doi:10.1109/ACSSC.2015.7421298

A minimax distortion view of differentially private query release

Weina Wang, Lei Ying, Junshan Zhang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Scopus citations

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 language	English (US)
Title of host publication	Conference Record - Asilomar Conference on Signals, Systems and Computers
Publisher	IEEE Computer Society
Pages	1046-1050
Number of pages	5
Volume	2016-February
ISBN (Print)	9781467385763
DOIs	https://doi.org/10.1109/ACSSC.2015.7421298
State	Published - Feb 26 2016
Event	49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015 - Pacific Grove, United States Duration: Nov 8 2015 → Nov 11 2015

Other

Other	49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015
Country/Territory	United States
City	Pacific Grove
Period	11/8/15 → 11/11/15

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing

Access to Document

10.1109/ACSSC.2015.7421298

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, 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

@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 = feb,

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",

note = "49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015 ; Conference date: 08-11-2015 Through 11-11-2015",

}

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

AN - SCOPUS:84969776444

SN - 9781467385763

VL - 2016-February

SP - 1046

EP - 1050

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

PB - IEEE Computer Society

T2 - 49th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015

Y2 - 8 November 2015 through 11 November 2015

ER -

A minimax distortion view of differentially private query release

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this