Distributed Bayesian learning with stochastic natural gradient expectation propagation and the posterior server

Leonard Hasenclever, Stefan Webb, Thibaut Lienart, Sebastian Vollmer, Balaji Lakshminarayanan, Charles Blundell, Yee Whye Teh
January 2017
Cite

Abstract

This paper makes two contributions to Bayesian machine learning algorithms. Firstly, we propose stochastic natural gradient expectation propagation (SNEP), a novel alternative to expectation propagation (EP), a popular variational inference algorithm. SNEP is a black …

Type
2
Publication
J. Mach. Learn. Res.
"Variational Inference" "Expectation Propagation" "Markov Chain Monte Carlo" "Posterior Server" "Parameter Server" "Large Scale Learning" "Stochastic Approximation" "Distributed Learning" "Deep Learning" "Bayesian Learning" "Natural Gradient"
Sebastian Vollmer
Sebastian Vollmer
Professor for Applications of Machine Learning

My research interests lie at the interface of applied probability, statistical inference and machine learning.