Skip to main content

Adversarial Learning of a Sampler Based on an Unnormalized Distribution

Publication ,  Conference
Li, C; Bai, K; Li, J; Wang, G; Chen, C; Carin, L
Published in: Proceedings of Machine Learning Research
January 1, 2019

We investigate adversarial learning in the case when only an unnormalized form of the density can be accessed, rather than samples. With insights so garnered, adversarial learning is extended to the case for which one has access to an unnormalized form u(x) of the target density function, but no samples. Further, new concepts in GAN regularization are developed, based on learning from samples or from u(x). The proposed method is compared to alternative approaches, with encouraging results demonstrated across a range of pplications, including deep soft Q-learning.

Duke Scholars

Published In

Proceedings of Machine Learning Research

EISSN

2640-3498

Publication Date

January 1, 2019

Volume

89

Start / End Page

3302 / 3311
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Li, C., Bai, K., Li, J., Wang, G., Chen, C., & Carin, L. (2019). Adversarial Learning of a Sampler Based on an Unnormalized Distribution. In Proceedings of Machine Learning Research (Vol. 89, pp. 3302–3311).
Li, C., K. Bai, J. Li, G. Wang, C. Chen, and L. Carin. “Adversarial Learning of a Sampler Based on an Unnormalized Distribution.” In Proceedings of Machine Learning Research, 89:3302–11, 2019.
Li C, Bai K, Li J, Wang G, Chen C, Carin L. Adversarial Learning of a Sampler Based on an Unnormalized Distribution. In: Proceedings of Machine Learning Research. 2019. p. 3302–11.
Li, C., et al. “Adversarial Learning of a Sampler Based on an Unnormalized Distribution.” Proceedings of Machine Learning Research, vol. 89, 2019, pp. 3302–11.
Li C, Bai K, Li J, Wang G, Chen C, Carin L. Adversarial Learning of a Sampler Based on an Unnormalized Distribution. Proceedings of Machine Learning Research. 2019. p. 3302–3311.

Published In

Proceedings of Machine Learning Research

EISSN

2640-3498

Publication Date

January 1, 2019

Volume

89

Start / End Page

3302 / 3311