Decentralized Optimization with Amplified Privacy via Efficient Communication
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909642501652480 |
|---|---|
| author | Huo, Wei Liu, Changxin Ding, Kemi Johansson, Karl Henrik Shi, Ling |
| author_facet | Huo, Wei Liu, Changxin Ding, Kemi Johansson, Karl Henrik Shi, Ling |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_07102 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Decentralized Optimization with Amplified Privacy via Efficient Communication Huo, Wei Liu, Changxin Ding, Kemi Johansson, Karl Henrik Shi, Ling Systems and Control 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. |
| title | Decentralized Optimization with Amplified Privacy via Efficient Communication |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2506.07102 |