Differentially private cloud-based multi-agent optimization with constraints

By Matthew T. Hale, Magnus Egerstedt. 2015

65 citations recorded by the source corpus.

We present an optimization framework that solves constrained multi-agent optimization problems while keeping each agent's state differentially private. The agents in the network seek to optimize a local objective function in the presence of global constraints. Agents communicate only through a trusted cloud computer and the cloud also performs computations based on global information. The cloud computer modifies the results of such computations before they are sent to the agents in order to guarantee that the agents' states are kept private. We show that under mild conditions each agent's optimization problem converges in mean-square to its unique solution while each agent's state is kept differentially private. A numerical simulation is provided to demonstrate the viability of this approach.

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

Recycled ADMM: Improving the Privacy and Accuracy of Distributed Algorithms (2019, background): “While a number of differentially private (sub)gradientbased distributed algorithms have been proposed [17]–[20], the same is much harder for ADMM-based algorithms due to its computational complexity stemming from the fact that each node is required to solve an optimization problem in each iteration.”
Differentially private distributed convex optimization via objective perturbation (2016, background): “More closely related to our present work are efforts [16]–[18] on differentially private distributed optimization for networked systems, where the sensitive information are the objective functions in [16], the optimization constraints in [17], and the agents’ states in [18].”
ADMM Based Privacy-Preserving Decentralized Optimization (2017, background): “In contrast to differential-privacy based optimization approaches [19]–[22], our approach can enable privacy preservation without sacrificing accuracy.”
Differentially Private Distributed Convex Optimization via Functional Perturbation (2015, background): “Of more relevance to our paper are recent works [17]–[19] that are focused on differentially private distributed optimization problems for multi-agent systems.”