arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.09396cs.DScs.LG
收藏

私有联邦频率估计:适应实例难度

Private Federated Frequency Estimation: Adapting to the Hardness of the Instance

Johns Hopkins University(约翰斯·霍普金斯大学);Google Research(谷歌研究院);Rice University(莱斯大学)

Jingfeng Wu, Wennan Zhu, Peter Kairouz, Vladimir Braverman

AI总结:

本文针对多轮联邦频率估计提出可证明更优的混合草图算法,并设计两阶段方法根据实例难度自适应设置草图大小,同时支持差分隐私,在大规模数据上验证了性能优势。

摘要:

在联邦频率估计(FFE)中,多个客户端通过一个服务器协同估计其集体数据的频率,该服务器遵守安全求和(SecSum)的隐私约束。SecSum是一种密码学多方计算协议,确保服务器只能访问客户端所持向量的总和。对于单轮FFE,已知计数草图(count sketching)在实现基本精度-通信权衡方面几乎是信息论最优的[Chen et al., 2022]。然而,我们证明,在更实用的多轮FFE设置下,对计数草图的简单改编严格次优,并提出一种新颖的混合草图算法,该算法可证明具有更高精度。我们还解决以下基本问题:实践者应如何设置草图大小,以使其适应底层问题的难度?我们提出一种两阶段方法,允许对较简单的问题(例如近稀疏或轻尾分布)使用较小的草图大小。我们通过展示如何将差分隐私添加到我们的算法中,并在大规模数据集上进行广泛实验验证其优越性能来结束本文。

英文摘要:

In federated frequency estimation (FFE), multiple clients work together to estimate the frequencies of their collective data by communicating with a server that respects the privacy constraints of Secure Summation (SecSum), a cryptographic multi-party computation protocol that ensures that the server can only access the sum of client-held vectors. For single-round FFE, it is known that count sketching is nearly information-theoretically optimal for achieving the fundamental accuracy-communication trade-offs [Chen et al., 2022]. However, we show that under the more practical multi-round FEE setting, simple adaptations of count sketching are strictly sub-optimal, and we propose a novel hybrid sketching algorithm that is provably more accurate. We also address the following fundamental question: how should a practitioner set the sketch size in a way that adapts to the hardness of the underlying problem? We propose a two-phase approach that allows for the use of a smaller sketch size for simpler problems (e.g., near-sparse or light-tailed distributions). We conclude our work by showing how differential privacy can be added to our algorithm and verifying its superior performance through extensive experiments conducted on large-scale datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑