{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/generative-adversarial-networks-as","title":"Generative Adversarial Networks as Variational Training of Energy Based Models","arxiv_id":"1611.01799","date":"2016-11-06","proceeding":null,"authors":["Shuangfei Zhai","Yu Cheng","Rogerio Feris","Zhongfei Zhang"],"abstract":"In this paper, we study deep generative models for effective unsupervised\nlearning. We propose VGAN, which works by minimizing a variational lower bound\nof the negative log likelihood (NLL) of an energy based model (EBM), where the\nmodel density $p(\\mathbf{x})$ is approximated by a variational distribution\n$q(\\mathbf{x})$ that is easy to sample from. The training of VGAN takes a two\nstep procedure: given $p(\\mathbf{x})$, $q(\\mathbf{x})$ is updated to maximize\nthe lower bound; $p(\\mathbf{x})$ is then updated one step with samples drawn\nfrom $q(\\mathbf{x})$ to decrease the lower bound. VGAN is inspired by the\ngenerative adversarial networks (GANs), where $p(\\mathbf{x})$ corresponds to\nthe discriminator and $q(\\mathbf{x})$ corresponds to the generator, but with\nseveral notable differences. We hence name our model variational GANs (VGANs).\nVGAN provides a practical solution to training deep EBMs in high dimensional\nspace, by eliminating the need of MCMC sampling. From this view, we are also\nable to identify causes to the difficulty of training GANs and propose viable\nsolutions. \\footnote{Experimental code is available at\nhttps://github.com/Shuangfei/vgan}","url_abs":"http://arxiv.org/abs/1611.01799v1","url_pdf":"http://arxiv.org/pdf/1611.01799v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"generative-adversarial-networks-as","repo_url":"https://github.com/Shuangfei/vgan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.01799","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}