From c0e746db37b7554092f6868444c44cd8d6d6a035 Mon Sep 17 00:00:00 2001 From: ChunyuanLI Date: Sat, 13 Jan 2018 02:11:32 -0500 Subject: [PATCH] Update README.md --- README.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index e86ceb7..485df35 100644 --- a/README.md +++ b/README.md @@ -3,16 +3,16 @@ **Tensorflow implementation of Stein Variational Gradient Descent (SVGD)** -
+ ![](/results/toy1.png) | :-------------------------:| ![](/results/toy2.png) | -
--- -Description: "SVGD is a general purpose variational inference algorithm that forms a natural counterpart of gradient descent for optimization. SVGD iteratively transports a set of particles to match with the target distribution, by applying a form of functional gradient descent that minimizes the KL divergence." -Link: +*Description*: "SVGD is a general purpose variational inference algorithm that forms a natural counterpart of gradient descent for optimization. SVGD iteratively transports a set of particles to match with the target distribution, by applying a form of functional gradient descent that minimizes the KL divergence." + + +*Link*: for official implementation information in Matlab and Theano, please visit the authors' project website - [SVGD](http://www.cs.dartmouth.edu/~dartml/project.html?p=vgd).