Distributed User-Level Private Mean Estimation
Distributed User-Level Private Mean Estimation
复制标题
DOI：
10.1109/isit50566.2022.9834713
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Antonious M. Girgis;Deepesh Data;S. Diggavi
中科院分区：
文献类型：
--
作者：
Antonious M. Girgis;Deepesh Data;S. Diggavi
传统上，项目级差分隐私框架已被研究的分布式学习中的应用。然而，当客户端有多个数据样本，并且可能希望隐藏其潜在的参与时，更合适的概念是用户级隐私[1]。在本文中，我们开发了一个分布式的私人优化框架，研究用户级的本地差分隐私保证和性能之间的权衡。这是一种新的分布式用户级私人均值估计算法，使用分布式私人重打击估计。我们使用这个结果来开发分布式优化的隐私性能权衡。
Traditionally, an item-level differential privacy framework has been studied for applications in distributed learning. However, when a client has multiple data samples, and might want to also hide its potential participation, a more appropriate notion is that of user-level privacy [1]. In this paper, we develop a distributed private optimization framework that studies the trade-off between user-level local differential privacy guarantees and performance. This is enabled by a novel distributed user-level private mean estimation algorithm using distributed private heavy-hitter estimation. We use this result to develop the privacy-performance trade-off for distributed optimization.