X2 generative adversarial network

Chenyang Tao*, Liqun Chen, Ricardo Henao, Jianfeng Feng, Lawrence Carin

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations


To assess the difference between real and synthetic data, Generative Adversarial Networks (GANs) are trained using a distribution discrepancy measure. Three widely employed measures are information-theoretic divergences, integral probability metrics, and Hilbert space discrepancy metrics. We elucidate the theoretical connections between these three popular GAN training criteria and propose a novel procedure, called x2-GAN, that is conceptually simple, stable at training and resistant to mode collapse. Our procedure naturally generalizes to address the problem of simultaneous matching of multiple distributions. Further, we propose a resampling strategy that significantly improves sample quality, by repurpos-ing the trained critic function via an importance weighting mechanism. Experiments show that the proposed procedure improves stability and convergence, and yields state-of-art results on a wide range of generative modeling tasks.

Original languageEnglish (US)
Title of host publication35th International Conference on Machine Learning, ICML 2018
EditorsAndreas Krause, Jennifer Dy
PublisherInternational Machine Learning Society (IMLS)
Number of pages10
ISBN (Electronic)9781510867963
StatePublished - 2018
Externally publishedYes
Event35th International Conference on Machine Learning, ICML 2018 - Stockholm, Sweden
Duration: Jul 10 2018Jul 15 2018

Publication series

Name35th International Conference on Machine Learning, ICML 2018


Conference35th International Conference on Machine Learning, ICML 2018

Bibliographical note

Publisher Copyright:
© 2018 by the Authors All rights reserved.

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Human-Computer Interaction
  • Software


Dive into the research topics of 'X2 generative adversarial network'. Together they form a unique fingerprint.

Cite this