.png){kind=icon}
返回
Dynamic Differential Privacy for ADMM-Based Distributed Classification Learning
.png){kind=icon}
OA
AI
DOI：10.1109/TIFS.2016.2607691.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Privacy-preserving distributed machine learning becomes increasingly important due to the recent rapid growth of data. This paper focuses on a class of regularized empirical risk minimization machine learning problems, and develops two methods to provide differential privacy to distributed learning algorithms over a network. We first decentralize the learning algorithm using the alternating direction method of multipliers, and propose the methods of dual variable perturbation and primal variable perturbation to provide dynamic differential privacy. The two mechanisms lead to algorithms that can provide privacy guarantees under mild conditions of the convexity and differentiability of the loss function and the regularizer. We study the performance of the algorithms, and show that the dual variable perturbation outperforms its primal counterpart. To design an optimal privacy mechanism, we analyze the fundamental tradeoff between privacy and accuracy, and provide guidelines to choose privacy parameters. Numerical experiments using customer information database are performed to corroborate the results on privacy and utility tradeoffs and design.
Keyword:
Machine learning
ADMM
distributed computing
privacy
differential privacy
dynamic programming
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8
论文数:
5.2K
被引数:
2.3W
机构
引用论文
The relationship of monodentate and bidentate coordinated uranium(VI) sulfate in aqueous solution
.png){kind=icon}
PREAI
分享收藏
分享收藏Low-Latency Multiuser Two-Way Wireless Relaying for Spectral and Energy Efficiencies低延迟多用户双向无线中继，实现频谱和能量效率OAAI
OAAI分享收藏Metachronal Swimming with Flexible Legs: A Kinematics Analysis of the Midwater Polychaete TomopterisOAAI
OAAI分享收藏分享收藏
查看更多内容