Papers › Generative Adversarial Networks as Variational Training of Energy Based Models
Generative Adversarial Networks as Variational Training of Energy Based Models
Shuangfei Zhai, Yu Cheng, Rogerio Feris, Zhongfei Zhang
In this paper, we study deep generative models for effective unsupervised learning. We propose VGAN, which works by minimizing a variational lower bound of the negative log likelihood (NLL) of an energy based model (EBM), where the model density p(𝐱) is approximated by a variational distribution q(𝐱) that is easy to sample from. The training of VGAN takes a two step procedure: given p(𝐱), q(𝐱) is updated to maximize the lower bound; p(𝐱) is then updated one step with samples drawn from q(𝐱) to decrease the lower bound. VGAN is inspired by the generative adversarial networks (GANs), where p(𝐱) corresponds to the discriminator and q(𝐱) corresponds to the generator, but with several notable differences. We hence name our model variational GANs (VGANs). VGAN provides a practical solution to training deep EBMs in high dimensional space, by eliminating the need of MCMC sampling. From this view, we are also able to identify causes to the difficulty of training GANs and propose viable solutions. \footnote{Experimental code is available at https://github.com/Shuangfei/vgan}
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections