|
Activity Number:
|
93
- Recent Advances in Statistical Inference on Network Data
|
|
Type:
|
Invited
|
|
Date/Time:
|
Monday, August 8, 2022 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
IMS
|
|
Abstract #320502
|
|
|
Title:
|
Edge Differentially Private Estimation in the Network Beta-Model via Jittering and Method of Moments
|
|
Author(s):
|
Jinyuan Chang and Qiao Hu and Eric Kolaczyk* and QIWEI YAO and Fengting Yi
|
|
Companies:
|
Southwestern University of Finance & Economics and Southwestern University of Finance & Economics and Boston University and London School of Economics and Southwestern University of Finance & Economics
|
|
Keywords:
|
adaptive inference;
bootstrap inference;
data privacy;
phase transition;
Stein's method
|
|
Abstract:
|
A standing challenge in data privacy is the trade-off between the level of privacy and the efficiency of statistical inference. Here we conduct an in-depth study of this trade-off for parameter estimation in the beta-model for edge differentially private network data released via jittering. Unlike most previous approaches based on maximum likelihood estimation for this network model, we proceed via method of moments. This choice facilitates our exploration of a substantially broader range of privacy levels -- corresponding to stricter privacy -- than has been to date. Over this new range we discover our proposed estimator for the parameters in the model exhibits an interesting phase transition, with both its convergence rate and asymptotic variance following one of three different regimes of behavior depending on the level of privacy. Because identification of the operable regime is difficult to impossible in practice, we devise a novel adaptive bootstrap procedure to construct uniform inference across different phases. Leveraging this bootstrap we are able to provide simultaneous inference of all parameters in the beta-model (i.e., for as many parameters as vertices).
|
Authors who are presenting talks have a * after their name.
