A Dual Perturbation Approach for Differential Private ADMM-Based Distributed Empirical Risk Minimization

By Tao Zhang, Quanyan Zhu. 2016

17 citations recorded by the source corpus.

The rapid growth of data has raised the importance of privacy-preserving techniques in distributed machine learning. In this paper, we develop a privacy-preserving method to a class of regularized empirical risk minimization (ERM) machine learning problems. We first decentralize the learning algorithm using the alternating direction method of multipliers (ADMM), and propose the method of dual variable perturbation to provide dynamic differential privacy. The mechanism leads to a privacy-preserving algorithm under mild conditions of the convexity and differentiability of the loss function and the regularizer. We study the performance of the algorithm measured by the number of data points required to achieve a bounded error. To design an optimal privacy mechanism, we analyze the fundamental tradeoff between privacy and accuracy, and provide guidelines to choose privacy parameters. Numerical experiments using the real-world database are performed to corroborate the results on the privacy and utility tradeoffs and design.

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

1. Peng Liu
2. Di Niu
3. Linglong Kong
4. Yaochen Hu

In Computer Networks and Communications

1. Peng Liu
2. Di Niu
3. Linglong Kong
4. Yaochen Hu

Citations in the corpus

• Learning Privately over Distributed Features: An ADMM Sharing Approach (2019, methodology): “Recently, DP has been applied to ADMM algorithms to solve multi-party machine learning problems Zhang et al. (2018); Zhang and Zhu (2016a); Zhang et al. (2019); Zhang and Zhu (2017).”