VAE Learning via Stein Variational Gradient Descent

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.

Authors

• Yuchen Pu Duke University
• Zhe Gan
• Ricardo Henao Duke University
• Chunyuan Li ByteDance Inc.
• Shaobo Han
• Lawrence Carin

Keywords

No keywords are indexed for this paper.