AISTATS 2018poster0 citations
Symmetric Variational Autoencoder and Connections to Adversarial Learning
Liqun Chen, Shuyang Dai, Yunchen Pu, Erjin Zhou, Chunyuan Li, Qinliang Su, Changyou Chen, Lawrence Carin
Abstract
A new form of the variational autoencoder (VAE) is proposed, based on the symmetric Kullback- Leibler divergence. It is demonstrated that learn- ing 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.
BibTeX
@InProceedings{pmlr-v84-chen18b,
title = {Symmetric Variational Autoencoder and Connections to Adversarial Learning},
author = {Chen, Liqun and Dai, Shuyang and Pu, Yunchen and Zhou, Erjin and Li, Chunyuan and Su, Qinliang and Chen, Changyou and Carin, Lawrence},
booktitle = {Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics},
pages = {661--669},
year = {2018},
editor = {Storkey, Amos and Perez-Cruz, Fernando},
volume = {84},
series = {Proceedings of Machine Learning Research},
month = {09--11 Apr},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v84/chen18b/chen18b.pdf},
url = {https://proceedings.mlr.press/v84/chen18b.html},
abstract = {A new form of the variational autoencoder (VAE) is proposed, based on the symmetric Kullback- Leibler divergence. It is demonstrated that learn- ing 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.}
}