Decentralized Optimization with Amplified Privacy via Efficient Communication
Abstract
Decentralized optimization is crucial for multi-agent systems, with significant concerns about communication efficiency and privacy. This paper explores the role of efficient communication in decentralized stochastic gradient descent algorithms for enhancing privacy preservation. We develop a novel algorithm that incorporates two key features: random agent activation and sparsified communication. Utilizing differential privacy, we demonstrate that these features reduce noise without sacrificing privacy, thereby amplifying the privacy guarantee and improving accuracy. Additionally, we analyze the convergence and the privacy-accuracy-communication trade-off of the proposed algorithm. Finally, we present experimental results to illustrate the effectiveness of our algorithm.
Keywords
Cite
@article{arxiv.2506.07102,
title = {Decentralized Optimization with Amplified Privacy via Efficient Communication},
author = {Wei Huo and Changxin Liu and Kemi Ding and Karl Henrik Johansson and Ling Shi},
journal= {arXiv preprint arXiv:2506.07102},
year = {2025}
}