Federated Generalized Bayesian Learning via Distributed Stein Variational Gradient Descent
From MaRDI portal
Publication:6349043
arXiv2009.06419MaRDI QIDQ6349043
Author name not available (Why is that?)
Publication date: 11 September 2020
Abstract: 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.
Has companion code repository: https://github.com/kclip/DSVGD
This page was built for publication: Federated Generalized Bayesian Learning via Distributed Stein Variational Gradient Descent
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6349043)
