A new method for learning variational autoencoders (VAEs) is developed, based on Stein variational gradient descent. A key advantage of this approach is that one need not make parametric assumptions about the form of the encoder distribution. Performance is further enhanced by integrating the proposed encoder with importance sampling. Excellent performance is demonstrated across multiple unsupervised and semi-supervised problems, including semi-supervised analysis of the ImageNet data, demonstrating the scalability of the model to large datasets.
@article{arxiv.1704.05155,
title = {VAE Learning via Stein Variational Gradient Descent},
author = {Yunchen Pu and Zhe Gan and Ricardo Henao and Chunyuan Li and Shaobo Han and Lawrence Carin},
journal= {arXiv preprint arXiv:1704.05155},
year = {2017}
}