Score: 1

Decentralized Optimization with Amplified Privacy via Efficient Communication

Published: June 8, 2025 | arXiv ID: 2506.07102v1

By: Wei Huo , Changxin Liu , Kemi Ding and more

Potential Business Impact:

Keeps secret messages safe while learning.

Business Areas:
A/B Testing Data and Analytics

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.

Country of Origin
πŸ‡¨πŸ‡³ πŸ‡­πŸ‡° πŸ‡ΈπŸ‡ͺ Sweden, China, Hong Kong

Page Count
12 pages

Category
Electrical Engineering and Systems Science:
Systems and Control