Full Citation
Title: Rényi Differentially Private ADMM for Non-Smooth Regularized Optimization
Citation Type: Conference Paper
Publication Year: 2020
ISBN: 9781450371070
ISSN:
DOI: 10.1145/3374664.3375733
NSFID:
PMCID:
PMID:
Abstract: In this paper we consider the problem of minimizing composite objective functions consisting of a convex differentiable loss function plus a non-smooth regularization term, such as $L_1$ norm or nuclear norm, under Rényi differential privacy (RDP). To solve the problem, we propose two stochastic alternating direction method of multipliers (ADMM) algorithms: ssADMM based on gradient perturbation and mpADMM based on output perturbation. Both algorithms decompose the original problem into sub-problems that have closed-form solutions. The first algorithm, ssADMM, applies the recent privacy amplification result for RDP to reduce the amount of noise to add. The second algorithm, mpADMM, numerically computes the sensitivity of ADMM variable updates and releases the updated parameter vector at the end of each epoch. We compare the performance of our algorithms with several baseline algorithms on both real and simulated datasets. Experimental results show that, in high privacy regimes (small ε), ssADMM and mpADMM outperform baseline algorithms in terms of classification and feature selection performance, respectively.
Url: https://dl.acm.org/doi/10.1145/3374664.3375733
User Submitted?: No
Authors: Chen, Chen; Lee, Jaewoo
Conference Name: Proceedings of the Tenth ACM Conference on Data and Application Security and Privacy
Publisher Location: New York, NY, USA
Data Collections: IPUMS USA
Topics: Other, Population Data Science
Countries: