arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.05529cs.LGcs.MA
收藏

异步扩散学习:代理子采样与本地更新

Asynchronous Diffusion Learning with Agent Subsampling and Local Updates

École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);Peking University(北京大学)

Elsa Rizk, Kun Yuan, Ali H. Sayed

AI总结:

本文研究异步代理网络中的扩散学习,代理自主决定参与时机和合作邻域,通过多次本地更新后传递结果,证明了策略在均方误差意义下稳定,并提供了联邦学习场景下的性能保证。

摘要:

本文研究了一个异步运行的代理网络,旨在发现适合各代理本地数据集的理想全局模型。我们假设每个代理独立决定参与算法的时机以及在任何给定时刻与邻域中哪个特定子集进行合作。当代理选择参与时,它会在将结果传递给子采样邻域之前进行多次本地更新。在此设置下,我们证明了所得到的异步扩散策略在均方误差意义上是稳定的,并专门针对联邦学习场景提供了性能保证。我们通过数值模拟展示了研究结果。

英文摘要:

In this work, we examine a network of agents operating asynchronously, aiming to discover an ideal global model that suits individual local datasets. Our assumption is that each agent independently chooses when to participate throughout the algorithm and the specific subset of its neighbourhood with which it will cooperate at any given moment. When an agent chooses to take part, it undergoes multiple local updates before conveying its outcomes to the sub-sampled neighbourhood. Under this setup, we prove that the resulting asynchronous diffusion strategy is stable in the mean-square error sense and provide performance guarantees specifically for the federated learning setting. We illustrate the findings with numerical simulations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑