Published in Arxiv, 2017
We propose a novel distributed inference algorithm for continuous graphical models by extending Stein variational gradient descent (SVGD) to leverage the Markov dependency structure of the distribution of interest.
D. Wang∗, Z. Zeng∗, and Q. Liu. Structured Stein Variational Inference for Continuous Graphical Models. ArXiv e-prints, November 2017. (∗Equal contribution, will submit to ICML 18) https://arxiv.org/abs/1711.07168