Duvenaud showed in Black-Box Stochastic Variational Inference in Five Lines of Python how to make use of the Python module autograd to easily code black-box variational inference introduced in Black Box Variational Inference by Ranganath et al.
I adapted his code to linear models.
You will need python 3 with autograd, matplotlib, and scipy.
-
Vprop: Variational Inference using RMSprop by Khan et al.:
As in this paper, I deliberately chose a prior of the form
$p(\boldsymbol{\theta})=\mathcal{N}(\boldsymbol{\theta}| \boldsymbol{0}, \boldsymbol{I}/\lambda)$ so that results can be compared to those obtained using the algorithm Vprop. - Automatic Variational Inference in Stan by Kucukelbir et al.: They automated black-box variational inference. What is great is that you can constraint the support of a random variable.
Laurent de Vito
All third-party libraries are subject to their own license.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
