Timezone: »

Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms
Xueru Zhang · Mohammad Mahdi Khalili · Mingyan Liu

Thu Jul 12 09:15 AM -- 12:00 PM (PDT) @ Hall B #168

Alternating direction method of multiplier (ADMM) is a popular method used to design distributed versions of a machine learning algorithm, whereby local computations are performed on local data with the output exchanged among neighbors in an iterative fashion. During this iterative process the leakage of data privacy arises. A differentially private ADMM was proposed in prior work (Zhang & Zhu, 2017) where only the privacy loss of a single node during one iteration was bounded, a method that makes it difficult to balance the tradeoff between the utility attained through distributed computation and privacy guarantees when considering the total privacy loss of all nodes over the entire iterative process. We propose a perturbation method for ADMM where the perturbed term is correlated with the penalty parameters; this is shown to improve the utility and privacy simultaneously. The method is based on a modified ADMM where each node independently determines its own penalty parameter in every iteration and decouples it from the dual updating step size. The condition for convergence of the modified ADMM and the lower bound on the convergence rate are also derived.

Author Information

Xueru Zhang (University of Michigan)
Mohammad Mahdi Khalili (University of Michigan)
Mingyan Liu (University of Michigan, Ann Arbor)

Mingyan Liu received her Ph.D. in electrical engineering from the University of Maryland, College Park, in 2000. She joined the Department of Electrical Engineering and Computer Science at the University of Michigan, Ann Arbor, in September 2000, where she is currently a Professor. Her research interests are in optimal resource allocation, sequential decision theory, incentive design, and performance modeling and analysis, all within the context of communication networks. Her most recent research activities involve online learning, modeling and mining of large scale Internet measurement data and the design of incentive mechanisms for cyber security.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors