Federated Generalized Bayesian Learning via Distributed Stein Variational Gradient Descent

• Published in: IEEE transactions on signal processing Vol. 70; pp. 2180 - 2192
• Main Authors: Kassab, Rahif, Simeone, Osvaldo
• Format: Journal Article
• Language: English
• Published: New York IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Bayes methods; Bayesian analysis; bayesian learning; Collaborative work; Convergence; Federated learning; Free energy; Iterative methods; Machine learning; Servers; Signal processing algorithms; Statistical inference; Training; Uncertainty; variational inference

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 po...