Scholars@Duke

VAE learning via Stein variational gradient descent

Publication ,  Conference
Pu, Y; Gan, Z; Henao, R; Li, C; Han, S; Carin, L
Published in: Advances in Neural Information Processing Systems
January 1, 2017

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.

Duke Scholars

Ricardo Henao
Author Ricardo Henao Biostatistics & Bioinformatics, Division of Translational Bi ...
Lawrence Carin
Author Lawrence Carin Electrical and Computer Engineering

Published In

Advances in Neural Information Processing Systems

ISSN

1049-5258

Publication Date

January 1, 2017

Volume

2017-December

Start / End Page

4237 / 4246

Related Subject Headings

  • 4611 Machine learning
  • 1702 Cognitive Sciences
  • 1701 Psychology
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Pu, Y., Gan, Z., Henao, R., Li, C., Han, S., & Carin, L. (2017). VAE learning via Stein variational gradient descent. In Advances in Neural Information Processing Systems (Vol. 2017-December, pp. 4237–4246).
Pu, Y., Z. Gan, R. Henao, C. Li, S. Han, and L. Carin. “VAE learning via Stein variational gradient descent.” In Advances in Neural Information Processing Systems, 2017-December:4237–46, 2017.
Pu Y, Gan Z, Henao R, Li C, Han S, Carin L. VAE learning via Stein variational gradient descent. In: Advances in Neural Information Processing Systems. 2017. p. 4237–46.
Pu, Y., et al. “VAE learning via Stein variational gradient descent.” Advances in Neural Information Processing Systems, vol. 2017-December, 2017, pp. 4237–46.
Pu Y, Gan Z, Henao R, Li C, Han S, Carin L. VAE learning via Stein variational gradient descent. Advances in Neural Information Processing Systems. 2017. p. 4237–4246.

Published In

Advances in Neural Information Processing Systems

ISSN

1049-5258

Publication Date

January 1, 2017

Volume

2017-December

Start / End Page

4237 / 4246

Related Subject Headings

  • 4611 Machine learning
  • 1702 Cognitive Sciences
  • 1701 Psychology