Message Passing Stein Variational Gradient Descent
[edit]
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:60186027, 2018.
Abstract
Stein variational gradient descent (SVGD) is a recently proposed particlebased Bayesian inference method, which has attracted a lot of interest due to its remarkable approximation ability and particle efficiency compared to traditional variational inference and Markov Chain Monte Carlo methods. However, we observed that particles of SVGD tend to collapse to modes of the target distribution, and this particle degeneracy phenomenon becomes more severe with higher dimensions. Our theoretical analysis finds out that there exists a negative correlation between the dimensionality and the repulsive force of SVGD which should be blamed for this phenomenon. We propose Message Passing SVGD (MPSVGD) to solve this problem. By leveraging the conditional independence structure of probabilistic graphical models (PGMs), MPSVGD converts the original highdimensional global inference problem into a set of local ones over the Markov blanket with lower dimensions. Experimental results show its advantages of preventing vanishing repulsive force in highdimensional space over SVGD, and its particle efficiency and approximation flexibility over other inference methods on graphical models.
Related Material


