当前位置: X-MOL 学术arXiv.cs.DS › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Lossless Compression of Efficient Private Local Randomizers
arXiv - CS - Data Structures and Algorithms Pub Date : 2021-02-24 , DOI: arxiv-2102.12099
Vitaly Feldman, Kunal Talwar

Locally Differentially Private (LDP) Reports are commonly used for collection of statistics and machine learning in the federated setting. In many cases the best known LDP algorithms require sending prohibitively large messages from the client device to the server (such as when constructing histograms over large domain or learning a high-dimensional model). This has led to significant efforts on reducing the communication cost of LDP algorithms. At the same time LDP reports are known to have relatively little information about the user's data due to randomization. Several schemes are known that exploit this fact to design low-communication versions of LDP algorithm but all of them do so at the expense of a significant loss in utility. Here we demonstrate a general approach that, under standard cryptographic assumptions, compresses every efficient LDP algorithm with negligible loss in privacy and utility guarantees. The practical implication of our result is that in typical applications the message can be compressed to the size of the server's pseudo-random generator seed. More generally, we relate the properties of an LDP randomizer to the power of a pseudo-random generator that suffices for compressing the LDP randomizer. From this general approach we derive low-communication algorithms for the problems of frequency estimation and high-dimensional mean estimation. Our algorithms are simpler and more accurate than existing low-communication LDP algorithms for these well-studied problems.

中文翻译:

有效的私有局部随机化器的无损压缩

本地差异专用(LDP)报告通常用于在联合设置中收集统计信息和机器学习。在许多情况下,最著名的LDP算法要求从客户端设备向服务器发送过大的消息(例如,在大域上构建直方图或学习高维模型时)。这导致在降低LDP算法的通信成本方面付出了巨大的努力。同时,由于随机化,已知LDP报告关于用户数据的信息相对较少。已知几种利用这一事实来设计LDP算法的低通信版本的方案,但是所有方案都以牺牲实用性为代价。在这里,我们演示了一种通用方法,在标准密码学假设下,压缩每一个有效的LDP算法,其私密性和实用性保证的损失可忽略不计。我们的结果的实际含义是,在典型的应用程序中,可以将消息压缩为服务器的伪随机生成器种子的大小。更一般地,我们将LDP随机化器的属性与足以压缩LDP随机化器的伪随机发生器的能力联系起来。从这种通用方法中,我们得出了针对频率估计和高维均值估计问题的低通信算法。对于这些经过充分研究的问题,我们的算法比现有的低通信LDP算法更简单,更准确。我们的结果的实际含义是,在典型的应用程序中,可以将消息压缩为服务器的伪随机生成器种子的大小。更一般地,我们将LDP随机化器的属性与足以压缩LDP随机化器的伪随机发生器的能力联系起来。从这种通用方法中,我们得出了针对频率估计和高维均值估计问题的低通信算法。对于这些经过充分研究的问题,我们的算法比现有的低通信LDP算法更简单,更准确。我们的结果的实际含义是,在典型的应用程序中,可以将消息压缩为服务器的伪随机生成器种子的大小。更一般地,我们将LDP随机化器的属性与足以压缩LDP随机化器的伪随机发生器的能力联系起来。从这种通用方法中,我们得出了针对频率估计和高维均值估计问题的低通信算法。对于这些经过充分研究的问题,我们的算法比现有的低通信LDP算法更简单,更准确。从这种通用方法中,我们得出了针对频率估计和高维均值估计问题的低通信算法。对于这些经过充分研究的问题,我们的算法比现有的低通信LDP算法更简单,更准确。从这种通用方法中,我们得出了针对频率估计和高维均值估计问题的低通信算法。对于这些经过充分研究的问题,我们的算法比现有的低通信LDP算法更简单,更准确。
更新日期:2021-02-25
down
wechat
bug