Skip to main content

Variational annealing of GANs: A Langevin perspective

Publication ,  Conference
Tao, C; Dai, S; Chen, L; Bai, K; Chen, J; Liu, C; Zhang, R; Bobashev, G; Carin, L
Published in: 36th International Conference on Machine Learning, ICML 2019
January 1, 2019

The generative adversarial network (GAN) has received considerable attention recently as a model for data synthesis, without an explicit specification of a likelihood function. There has been commensurate interest in leveraging likelihood estimates to improve GAN training. To enrich the understanding of this fast-growing yet almost exclusively heuristic-driven subject, we elucidate the theoretical roots of some of the empirical attempts to stabilize and improve GAN training with the introduction of likelihoods. We highlight new insights from variational theory of diffusion processes to derive a likelihood-based regularizing scheme for GAN training, and present a novel approach to train GANs with an unnormalized distribution instead of empirical samples. To substantiate our claims, we provide experimental evidence on how our theoretically-inspired new algorithms improve upon current practice.

Duke Scholars

Published In

36th International Conference on Machine Learning, ICML 2019

Publication Date

January 1, 2019

Volume

2019-June

Start / End Page

10777 / 10786
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Tao, C., Dai, S., Chen, L., Bai, K., Chen, J., Liu, C., … Carin, L. (2019). Variational annealing of GANs: A Langevin perspective. In 36th International Conference on Machine Learning, ICML 2019 (Vol. 2019-June, pp. 10777–10786).
Tao, C., S. Dai, L. Chen, K. Bai, J. Chen, C. Liu, R. Zhang, G. Bobashev, and L. Carin. “Variational annealing of GANs: A Langevin perspective.” In 36th International Conference on Machine Learning, ICML 2019, 2019-June:10777–86, 2019.
Tao C, Dai S, Chen L, Bai K, Chen J, Liu C, et al. Variational annealing of GANs: A Langevin perspective. In: 36th International Conference on Machine Learning, ICML 2019. 2019. p. 10777–86.
Tao, C., et al. “Variational annealing of GANs: A Langevin perspective.” 36th International Conference on Machine Learning, ICML 2019, vol. 2019-June, 2019, pp. 10777–86.
Tao C, Dai S, Chen L, Bai K, Chen J, Liu C, Zhang R, Bobashev G, Carin L. Variational annealing of GANs: A Langevin perspective. 36th International Conference on Machine Learning, ICML 2019. 2019. p. 10777–10786.

Published In

36th International Conference on Machine Learning, ICML 2019

Publication Date

January 1, 2019

Volume

2019-June

Start / End Page

10777 / 10786