TY - GEN
T1 - Divergence triangle for joint training of generator model, energy-based model, and inferential model
AU - Han, Tian
AU - Nijkamp, Erik
AU - Fang, Xiaolin
AU - Hill, Mitch
AU - Zhu, Song Chun
AU - Wu, Ying Nian
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - This paper proposes the divergence triangle as a framework for joint training of a generator model, energy-based model and inference model. The divergence triangle is a compact and symmetric (anti-symmetric) objective function that seamlessly integrates variational learning, adversarial learning, wake-sleep algorithm, and contrastive divergence in a unified probabilistic formulation. This unification makes the processes of sampling, inference, and energy evaluation readily available without the need for costly Markov chain Monte Carlo methods. Our experiments demonstrate that the divergence triangle is capable of learning (1) an energy-based model with well-formed energy landscape, (2) direct sampling in the form of a generator network, and (3) feed-forward inference that faithfully reconstructs observed as well as synthesized data.
AB - This paper proposes the divergence triangle as a framework for joint training of a generator model, energy-based model and inference model. The divergence triangle is a compact and symmetric (anti-symmetric) objective function that seamlessly integrates variational learning, adversarial learning, wake-sleep algorithm, and contrastive divergence in a unified probabilistic formulation. This unification makes the processes of sampling, inference, and energy evaluation readily available without the need for costly Markov chain Monte Carlo methods. Our experiments demonstrate that the divergence triangle is capable of learning (1) an energy-based model with well-formed energy landscape, (2) direct sampling in the form of a generator network, and (3) feed-forward inference that faithfully reconstructs observed as well as synthesized data.
KW - Deep Learning
KW - Image and Video Synthesis
KW - Statistical Learning
UR - http://www.scopus.com/inward/record.url?scp=85077183113&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077183113&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2019.00887
DO - 10.1109/CVPR.2019.00887
M3 - Conference contribution
AN - SCOPUS:85077183113
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 8662
EP - 8671
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Y2 - 16 June 2019 through 20 June 2019
ER -