A manifold-based variational Bayes algorithm with natural-gradient updates is shown to converge at O(1/sqrt(T)) for non-convex ELBOs and faster under retraction-convexity, with Gaussian and Wishart implementations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Variational Bayes on Manifolds
A manifold-based variational Bayes algorithm with natural-gradient updates is shown to converge at O(1/sqrt(T)) for non-convex ELBOs and faster under retraction-convexity, with Gaussian and Wishart implementations.