# Connecting Federated ADMM to Bayes Source: [Connecting Federated ADMM to Bayes]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:48:55.522Z Authors: Siddharth Swaroop, Mohammad Emtiyaz Khan, Finale Doshi-Velez Published: 2025-01-28T22:37:25.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on Fashion-MNIST heterogeneous (test)](): Image Classification; Fashion-MNIST heterogeneous (test); Test Accuracy: 83. - [Image Classification on MNIST 100 clients, highly heterog. (test)](): Image Classification; MNIST 100 clients, highly heterog. (test); Test Accuracy: 94.9. - [Image Classification on CIFAR-100 10 clients, heterog. (test)](): Image Classification; CIFAR-100 10 clients, heterog. (test); Test Accuracy: 40.4. - [Image Classification on FashionMNIST (test)](): Image Classification; FashionMNIST (test); Accuracy: not recorded. ## Original sources and implementation [Original paper]() [PDF]()