This paper investigates the use of the cubic-regularized Newton method within a federated learning framework while addressing two major concerns that commonly arise in federated learning: privacy leakage and communication bottleneck. We introduce a federated learning algorithm called Differentially Private Federated Cubic Regularized Newton (DP-FCRN). By leveraging second-order techniques, our algorithm achieves lower iteration complexity compared to first-order methods. We also incorporate noise perturbation during local computations to ensure privacy. Furthermore, we employ sparsification in uplink transmission, which not only reduces the communication costs but also amplifies the privacy guarantee. Specifically, this approach reduces the necessary noise intensity without compromising privacy protection. We analyze the convergence properties of our algorithm and establish the privacy guarantee. Finally, we validate the effectiveness of the proposed algorithm through experiments on a benchmark dataset.

本文解决了联邦学习中隐私泄露和通信瓶颈的两个主要问题，提出了一种新的算法——差分隐私联邦立方正则牛顿（DP-FCRN）。通过利用二阶技术，该算法在迭代复杂度上优于一阶方法，同时在本地计算中加入噪声扰动以确保隐私，且通过稀疏化传输降低通信成本并增强隐私保证。本研究的重要发现是，新的算法在保护隐私的前提下，降低了所需的噪声强度，并在基准数据集上验证了其有效性。

具有稀疏化增强差分隐私的联邦立方正则牛顿学习