VAE Learning via Stein Variational Gradient Descent

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.

arXiv commentAccepted to NIPS 2017

Cited by in corpus (12)

• A Non-Asymptotic Analysis for Stein Variational Gradient Descent
• Metrizing Weak Convergence with Maximum Mean Discrepancies
• Sliced Kernelized Stein Discrepancy
• The reproducing Stein kernel approach for post-hoc corrected sampling
• Semantics Preserving Adversarial Learning
• Implicit Deep Latent Variable Models for Text Generation
• Kernel Stein Generative Modeling
• Variational Inference with Holder Bounds
• Stein Variational Gaussian Processes
• Understanding MCMC Dynamics as Flows on the Wasserstein Space
• Loss function based second-order Jensen inequality and its application to particle variational inference
• Symmetric Wasserstein Autoencoders