Dynamic Differential Privacy for ADMM-Based Distributed Classification Learning

By Tao Zhang, Quanyan Zhu. 2017

194 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

Citations in the corpus

Learning Privately over Distributed Features: An ADMM Sharing Approach (2019, methodology): “As-sumption 2.2 comes from Zhang and Zhu (2016b) and Assumption 2.3 comes from Zhang and Zhu (2016b) and Sarwate and Chaudhuri (2013).”
The Value of Collaboration in Convex Machine Learning with Differential Privacy (2019, background): “In [20], [21], the privacy budget was kept constant and therefore by communicating more, as the number of the iterations grows, the privacy guarantee weakens.”
Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms (2018, methodology): “This issue of step size never arises in the study of (Zhang & Zhu, 2017) because the analysis is only for a single iteration; however, as we have seen doing so leads to signiﬁcant total privacy loss over many iterations.”
Recycled ADMM: Improving the Privacy and Accuracy of Distributed Algorithms (2019, methodology): “In particular, Zhang and Zhu [21] proposes the dual/primal variable perturbation method to inspect the privacy loss of one node in every single iteration; this, however, is not sufficient for guaranteeing privacy as an adversary can potentially use the revealed results from all iterations to perform”
DP-ADMM: ADMM-Based Distributed Learning With Differential Privacy (2018, methodology): “Among the works on distributed learning with differential privacy, most of them focus on subgradient-based algorithms [35]–[38] and only a few works consider ADMMbased methods [1], [2], [17]–[19].”
ADMM Based Privacy-Preserving Decentralized Optimization (2017, background): “In recent years, decentralized optimization has been playing key roles in applications as diverse as rendezvous in multiagent systems [1], spectrum sensing in cognitive networks [2], support vector machine in machine learning [3], online learning [4], classification [5], data regression in statistic”
Locally Differentially Private Data Collection and Analysis (2019, background): “One of the many topics in DP research is differentially private empirical risk minimization for machine learning [18, 10], especially for deep neural networks [1, 40, 59, 2, 53].”
Securing Fog Computing for Internet of Things Applications: Challenges and Solutions (2018, background): “Zhang and Zhu [211] studied regularized empirical risk minimization machine learning problems, and proposed dual variable perturbation and primal variable perturbation to realize dynamic differential privacy.”