Oral
Composite Functional Gradient Learning of Generative Adversarial Models
Rie Johnson · Tong Zhang

Thu Jul 12th 01:30 -- 01:50 PM @ A7

This paper first presents a theory for generative adversarial methodsthat does not rely on the traditional minimax formulation. It shows that with a strong discriminator, a good generator can be learned so thatthe KL divergence between the distributions of real data and generated data improves after each functional gradient step until it converges to zero. Based on the theory, we propose a new stable generative adversarial method.A theoretical insight into the original GAN from this new viewpoint is also provided. The experiments on image generation show the effectiveness of our new method.

Author Information

Rie Johnson (RJ Research Consulting)
Tong Zhang (Tecent AI Lab)
Tong Zhang

Tong Zhang is a professor of Computer Science and Mathematics at the Hong Kong University of Science and Technology. His research interests are machine learning, big data and their applications. He obtained a BA in Mathematics and Computer Science from Cornell University, and a PhD in Computer Science from Stanford University. Before joining HKUST, Tong Zhang was a professor at Rutgers University, and worked previously at IBM, Yahoo as research scientists, Baidu as the director of Big Data Lab, and Tencent as the founding director of AI Lab. Tong Zhang was an ASA fellow and IMS fellow, and has served as the chair or area-chair in major machine learning conferences such as NIPS, ICML, and COLT, and has served as associate editors in top machine learning journals such as PAMI, JMLR, and Machine Learning Journal.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors