Skip to main content

Symmetric Variational Autoencoder and Connections to Adversarial Learning

Publication ,  Conference
Chen, L; Dai, S; Pu, Y; Zhou, E; Li, C; Su, Q; Chen, C; Carin, L
Published in: Proceedings of Machine Learning Research
January 1, 2018

A new form of the variational autoencoder (VAE) is proposed, based on the symmetric KullbackLeibler divergence. It is demonstrated that learning of the resulting symmetric VAE (sVAE) has close connections to previously developed adversarial-learning methods. This relationship helps unify the previously distinct techniques of VAE and adversarially learning, and provides insights that allow us to ameliorate shortcomings with some previously developed adversarial methods. In addition to an analysis that motivates and explains the sVAE, an extensive set of experiments validate the utility of the approach.

Duke Scholars

Published In

Proceedings of Machine Learning Research

EISSN

2640-3498

Publication Date

January 1, 2018

Volume

84
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Chen, L., Dai, S., Pu, Y., Zhou, E., Li, C., Su, Q., … Carin, L. (2018). Symmetric Variational Autoencoder and Connections to Adversarial Learning. In Proceedings of Machine Learning Research (Vol. 84).
Chen, L., S. Dai, Y. Pu, E. Zhou, C. Li, Q. Su, C. Chen, and L. Carin. “Symmetric Variational Autoencoder and Connections to Adversarial Learning.” In Proceedings of Machine Learning Research, Vol. 84, 2018.
Chen L, Dai S, Pu Y, Zhou E, Li C, Su Q, et al. Symmetric Variational Autoencoder and Connections to Adversarial Learning. In: Proceedings of Machine Learning Research. 2018.
Chen, L., et al. “Symmetric Variational Autoencoder and Connections to Adversarial Learning.” Proceedings of Machine Learning Research, vol. 84, 2018.
Chen L, Dai S, Pu Y, Zhou E, Li C, Su Q, Chen C, Carin L. Symmetric Variational Autoencoder and Connections to Adversarial Learning. Proceedings of Machine Learning Research. 2018.

Published In

Proceedings of Machine Learning Research

EISSN

2640-3498

Publication Date

January 1, 2018

Volume

84