TY - GEN
T1 - Adversarial learning of a sampler based on an unnormalized distribution
AU - Li, Chunyuan
AU - Bai, Ke
AU - Li, Jianqiao
AU - Wang, Guoyin
AU - Chen, Changyou
AU - Carin, Lawrence
N1 - Generated from Scopus record by KAUST IRTS on 2021-02-09
PY - 2020/1/1
Y1 - 2020/1/1
N2 - 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 applications, including deep soft Q-learning.
AB - 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 applications, including deep soft Q-learning.
UR - http://www.scopus.com/inward/record.url?scp=85084982132&partnerID=8YFLogxK
M3 - Conference contribution
BT - AISTATS 2019 - 22nd International Conference on Artificial Intelligence and Statistics
PB - PLMR
ER -