这篇论文搞了个VRA-FedSGD，专门对付联邦学习里常见的重尾噪声，收敛速度有理论保证，实验也跑通了，值得看看。
论文提出VRA-FedSGD算法，针对联邦学习中重尾梯度噪声和通信噪声问题。该算法采用动量方差缩减配合非线性映射减轻重尾梯度噪声，并使用方差缩减聚合机制抑制重尾通信噪声。在非凸目标函数下，均方收敛率为O(K^{-(p-1)/(2p-1)})，其中p为尾指数；在强凸目标函数下，几乎必然收敛率为O~(K^{-(1-1/(p-ε))})。在逻辑回归问题上的仿真实验验证了算法有效性。
Federated learning with heavy-tailed gradient noise and communication noise: a variance-reduction based algorithm
Federated learning (FL) is an emerging distributed machine learning paradigm that enables local devices to jointly train a global model while keeping data decentralized and private. We propose a variance-reduction based algorithm, VRA-FedSGD, for FL in the presence of heavy-tailed gradient noise and communication noise, where these noises are prevalent in large-scale machine learning over wireless networks and Internet of Things deployments. VRA-FedSGD employs a momentum variance reduction technique together with a nonlinear mapping to mitigate heavy-tailed gradient noise, and uses a variance-reduced aggregation mechanism to suppress heavy-tailed communication noise. In the mean sense, VRA-FedSGD achieves a convergence rate of {\small$\mathcal{O}\left(K^{-(p-1)/(2p-1)}\right)$} for nonconvex objective functions, where $p$ is the tail index of heavy-tailed noise. In the almost sure sense, VRA-FedSGD achieves a convergence rate of $\tilde{\mathcal{O}}\left(K^{-(1-1/(p-ε))}\right)$ for strongly convex objective functions, where $ε$ is an arbitrarily small constant. Simulated experiments on a logistic regression problem with real-world data verify the effectiveness of VRA-FedSGD.