In private federated learning (FL), a server aggregates differentially private updates from a large number of clients in order to train a machine learning model. The main challenge in this setting is balancing privacy with both classification accuracy of the learnt model as well as the number of bits communicated between the clients and server. Prior work has achieved a good trade-off by designing a privacy-aware compression mechanism, called the minimum variance unbiased (MVU) mechanism, that numerically solves an optimization problem to determine the parameters of the mechanism. This paper builds upon it by introducing a new interpolation procedure in the numerical design process that allows for a far more efficient privacy analysis. The result is the new Interpolated MVU mechanism that is more scalable, has a better privacy-utility trade-off, and provides SOTA results on communication-efficient private FL on a variety of datasets.

翻译：在隐私联邦学习中，服务器通过聚合来自大量客户端的差分隐私更新来训练机器学习模型。该场景面临的核心挑战在于平衡隐私保护、模型分类精度以及客户端与服务器之间的通信比特数。以往工作通过设计一种称为最小方差无偏（MVU）机制的隐私感知压缩机制实现了良好权衡，该机制通过数值求解优化问题来确定机制参数。本文在此基础上引入了一种新的插值方法，在数值设计过程中实现了更高效的隐私分析。由此产生的插值MVU机制具有更强的可扩展性，更优的隐私-效用权衡，并在多个数据集上实现了通信高效私有联邦学习的最新成果。