Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.07482 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914229037039616 |
|---|---|
| author | Xie, Furan Liu, Bing Chai, Li |
| author_facet | Xie, Furan Liu, Bing Chai, Li |
| contents | In this paper, we investigate the problem of differentially private distributed optimization. Recognizing that lower sensitivity leads to higher accuracy, we analyze the key factors influencing the sensitivity of differentially private distributed algorithms. Building on these insights, we propose a novel differentially private distributed algorithm for undirected graphs that enhances optimization accuracy by reducing sensitivity. To ensure practical applicability, we derive an explicit closed-form expression for the noise parameter as a function of the privacy budget. Moreover, we rigorously prove that the proposed algorithm can achieve arbitrarily rigorous $ε$-differential privacy, establish its convergence in the mean square sense, and provide an upper bound on its optimization accuracy. Finally, extensive comparisons with various privacy-preserving methods validate the effectiveness of our algorithm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_07482 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Accuracy in Differentially Private Distributed Optimization Through Sensitivity Reduction Xie, Furan Liu, Bing Chai, Li Optimization and Control In this paper, we investigate the problem of differentially private distributed optimization. Recognizing that lower sensitivity leads to higher accuracy, we analyze the key factors influencing the sensitivity of differentially private distributed algorithms. Building on these insights, we propose a novel differentially private distributed algorithm for undirected graphs that enhances optimization accuracy by reducing sensitivity. To ensure practical applicability, we derive an explicit closed-form expression for the noise parameter as a function of the privacy budget. Moreover, we rigorously prove that the proposed algorithm can achieve arbitrarily rigorous $ε$-differential privacy, establish its convergence in the mean square sense, and provide an upper bound on its optimization accuracy. Finally, extensive comparisons with various privacy-preserving methods validate the effectiveness of our algorithm. |
| title | Enhancing Accuracy in Differentially Private Distributed Optimization Through Sensitivity Reduction |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2505.07482 |