.png){kind=icon}
返回
Differentially private distributed online mirror descent algorithm
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2023.126531.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper examines a private distributed online convex optimization problem in which each agent strives to minimize the sum of objective functions while also tending to keep their individual objective functions confidential. We use differential privacy as the metric to safeguard each agent's privacy and offer a distributed online mirror descent technique that is differentially private. We demonstrate that for strongly convex objective functions, our proposed algorithm satisfies the expected regret bound of O(ln (T)) while maintaining differential privacy, where T is the number of iterations. The established expected regret bound matches the optimal theoretical regret bound with respect to T. We further illu-minate the trade-off between the extent of privacy-preserving and the expected regret bound through numerical simulations.& COPY; 2023 Elsevier B.V. All rights reserved.
Keyword:
Differential privacy
Distributed online optimization
Mirror descent
Expected regret
Strongly convex
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Federated learning of predictive models from federated Electronic Health Records从联邦电子健康记录中联合学习预测模型
OAAI
OAAI分享收藏Distributed optimization of first-order discrete-time multi-agent systems with event-triggered communication.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏分享收藏Individual Regret Bounds for the Distributed Online Alternating Direction Method of Multipliers
PREAI
分享收藏
查看更多内容