CIF: Small: Foundations of Decentralized Data Science: Optimizing Utility, Privacy and Communication Efficiency

移动设备、传感器和服务器每天生成的海量数据有望带来前所未有的推理能力，从而彻底改变从医学、工程到基础设施等众多行业和科学领域。由于通信网络的带宽限制，将这些数据集中到单个位置的传统数据科学变得越来越不现实。共享专有、个人或敏感数据的法律、行政和道德约束对实现这一承诺提出了进一步的挑战。 该项目追求以下问题：人们是否可以从整个网络生成的数据中提取价值，而无需在单个位置收集和处理数据？该项目的总体目标是利用分布式数据的推理能力，而不会产生传统数据收集带来的系统性隐私风险和成本。该项目追求广泛的规范数据科学任务的去中心化方案，这些任务交换小范围的消息以完成所需的任务。这些消息旨在保护用户数据的隐私及其敏感特征，同时最大限度地降低总通信成本。因此，它们在所需任务的准确性、用户数据的隐私性和通信效率之间提供了最佳权衡。这些方案适应底层数据和网络的结构，并且在可用时可以利用数据的低内在维度和网络上的多轮交互。该项目还开发了信息论性能基准，描述在隐私和通信限制下不可能发生的事情，并在各种标准下确定所提议方案的最优性。因此，该项目为去中心化数据科学提供了严格而全面的理论基础，使许多规范任务能够在分布式数据上高效、私密地实施。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

The deluge of data generated daily across mobile devices, sensors, and servers holds the promise of unprecedented inferential power to revolutionize numerous industries and scientific domains, from medicine, to engineering, to infrastructure. Traditional data science that pools this data to a single location is becoming increasingly unrealistic due to bandwidth limitations in communication networks. Legal, administrative, and ethical constraints in sharing proprietary, personal, or sensitive data pose further challenges on the path to realizing this promise. The project pursues the following query: Can one extract value from data generated across an entire network without having to collect and process it in a single location?The broad goal of this project is to harness the inferential power of distributed data without the systemic privacy risks and costs resulting from traditional data collection. The project pursues decentralized schemes for a wide range of canonical data science tasks that exchange narrowly scoped messages to complete the desired task. These messages are designed to preserve the privacy of the user data and its sensitive characteristics while minimizing the total communication cost. As a result, they provide optimal trade-offs between accuracy for the desired task, privacy for the user data, and communication efficiency. The schemes adapt to the structure of the underlying data and network and, when available, can leverage low intrinsic dimensionality of the data and multi-round interactions over the network. This project also develops information-theoretic performance benchmarks that delineate what is impossible under privacy and communication constraints and establish optimality of the proposed schemes under various criteria. As such, the project delivers a rigorous and comprehensive theoretical foundation for decentralized data science that allows many canonical tasks to be efficiently and privately implemented on distributed data.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.