Skip to yearly menu bar Skip to main content


Poster

VAE Learning via Stein Variational Gradient Descent

Yuchen Pu · Zhe Gan · Ricardo Henao · Chunyuan Li · Shaobo Han · Lawrence Carin

Pacific Ballroom #121

Keywords: [ Variational Inference ] [ Semi-Supervised Learning ] [ Deep Autoencoders ] [ Density Estimation ]


Abstract:

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.

Live content is unavailable. Log in and register to view live content