将联邦ADMM与变分贝叶斯联系起来，提升学习性能
Connecting Federated ADMM to Bayes
- 用变分贝叶斯的‘站点’参数推导出ADMM对偶变量
- 提出两种新版本ADMM，分别支持灵活协方差和函数正则化
- 实验验证性能提升，适合研究联邦学习理论与算法者
我们建立了基于ADMM与变分贝叶斯（VB）的两种不同联邦学习方法之间的新联系，并通过融合其互补优势提出新变体。具体而言，我们证明了ADMM中的对偶变量可自然地由使用各向同性高斯协方差的VB中‘站点’参数导出。基于此，我们从VB推导出两种新的ADMM版本：一种采用灵活协方差，另一种引入函数正则化。数值实验验证了性能改进。该工作揭示了原本被认为本质不同的两个领域之间的深层联系，并结合二者以增强联邦学习效果。
原文摘要 · Abstract (English)
We provide new connections between two distinct federated learning approaches based on (i) ADMM and (ii) Variational Bayes (VB), and propose new variants by combining their complementary strengths. Specifically, we show that the dual variables in ADMM naturally emerge through the 'site' parameters used in VB with isotropic Gaussian covariances. Using this, we derive two versions of ADMM from VB that use flexible covariances and functional regularisation, respectively. Through numerical experiments, we validate the improvements obtained in performance. The work shows connection between two fields that are believed to be fundamentally different and combines them to improve federated learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。