- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- UBC Faculty Research and Publications /
- ABCDP: Approximate Bayesian Computation with Differential...
Open Collections
UBC Faculty Research and Publications
ABCDP: Approximate Bayesian Computation with Differential Privacy Park, Mijung; Vinaroz, Margarita; Jitkrittum, Wittawat
Abstract
We developed a novel approximate Bayesian computation (ABC) framework, ABCDP, which produces differentially private (DP) and approximate posterior samples. Our framework takes advantage of the sparse vector technique (SVT), widely studied in the differential privacy literature. SVT incurs the privacy cost only when a condition (whether a quantity of interest is above/below a threshold) is met. If the condition is sparsely met during the repeated queries, SVT can drastically reduce the cumulative privacy loss, unlike the usual case where every query incurs the privacy loss. In ABC, the quantity of interest is the distance between observed and simulated data, and only when the distance is below a threshold can we take the corresponding prior sample as a posterior sample. Hence, applying SVT to ABC is an organic way to transform an ABC algorithm to a privacy-preserving variant with minimal modification, but yields the posterior samples with a high privacy level. We theoretically analyzed the interplay between the noise added for privacy and the accuracy of the posterior samples. We apply ABCDP to several data simulators and show the efficacy of the proposed framework.
Item Metadata
Title |
ABCDP: Approximate Bayesian Computation with Differential Privacy
|
Creator | |
Publisher |
Multidisciplinary Digital Publishing Institute
|
Date Issued |
2021-07-27
|
Description |
We developed a novel approximate Bayesian computation (ABC) framework, ABCDP, which produces differentially private (DP) and approximate posterior samples. Our framework takes advantage of the sparse vector technique (SVT), widely studied in the differential privacy literature. SVT incurs the privacy cost only when a condition (whether a quantity of interest is above/below a threshold) is met. If the condition is sparsely met during the repeated queries, SVT can drastically reduce the cumulative privacy loss, unlike the usual case where every query incurs the privacy loss. In ABC, the quantity of interest is the distance between observed and simulated data, and only when the distance is below a threshold can we take the corresponding prior sample as a posterior sample. Hence, applying SVT to ABC is an organic way to transform an ABC algorithm to a privacy-preserving variant with minimal modification, but yields the posterior samples with a high privacy level. We theoretically analyzed the interplay between the noise added for privacy and the accuracy of the posterior samples. We apply ABCDP to several data simulators and show the efficacy of the proposed framework.
|
Subject | |
Genre | |
Type | |
Language |
eng
|
Date Available |
2021-09-03
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
CC BY 4.0
|
DOI |
10.14288/1.0401911
|
URI | |
Affiliation | |
Citation |
Entropy 23 (8): 961 (2021)
|
Publisher DOI |
10.3390/e23080961
|
Peer Review Status |
Reviewed
|
Scholarly Level |
Faculty
|
Rights URI | |
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
CC BY 4.0