This paper introduces Distributed Stein Variational Gradient Descent (DSVGD), a non-parametric generalized Bayesian inference framework for federated learning. DSVGD maintains a number of non-random and interacting particles at a central server to represent the current iterate of the model global posterior. The particles are iteratively downloaded and updated by one of the agents with the end goal of minimizing the global free energy. By varying the number of particles, DSVGD enables a flexible trade-off between per-iteration communication load and number of communication rounds. DSVGD is shown to compare favorably to benchmark frequentist and Bayesian federated learning strategies, also scheduling a single device per iteration, in terms of accuracy and scalability with respect to the number of agents, while also providing well-calibrated, and hence trustworthy, predictions.

翻译：本文介绍分散式 Stein Variation 梯度底部(DSVGD),这是一个用于联合学习的非参数性通用贝叶斯推断框架,DSVGD在一个中央服务器上维持一些非随机和互动的粒子,以代表模型全球后继器的当前迭代。粒子由其中一个代理商进行迭代下载和更新,最终目标是最大限度地减少全球自由能源。DSVGD通过粒子数量的不同,使得实时通信负荷与通信轮数之间的灵活取舍。DSVGD显示,它比照常客和巴伊西亚联邦化学习战略的基准,并且从精确性和可缩放性的角度对各种物剂的数量安排一个单一的迭代点,同时提供精确校准的预测,因而是可信的。