{"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/calibrating-energy-based-generative","title":"Calibrating Energy-based Generative Adversarial Networks","arxiv_id":"1702.01691","date":"2017-02-06","proceeding":null,"authors":["Zihang Dai","Amjad Almahairi","Philip Bachman","Eduard Hovy","Aaron Courville"],"abstract":"In this paper, we propose to equip Generative Adversarial Networks with the\nability to produce direct energy estimates for samples.Specifically, we propose\na flexible adversarial training framework, and prove this framework not only\nensures the generator converges to the true data distribution, but also enables\nthe discriminator to retain the density information at the global optimal. We\nderive the analytic form of the induced solution, and analyze the properties.\nIn order to make the proposed framework trainable in practice, we introduce two\neffective approximation techniques. Empirically, the experiment results closely\nmatch our theoretical analysis, verifying the discriminator is able to recover\nthe energy of data distribution.","url_abs":"http://arxiv.org/abs/1702.01691v2","url_pdf":"http://arxiv.org/pdf/1702.01691v2.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":"calibrating-energy-based-generative","repo_url":"https://github.com/zihangdai/cegan_iclr2017","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conditional-image-generation-on-cifar-10","task":"Conditional Image Generation","dataset":"CIFAR-10","model":"EGAN-Ent-VI","rank_in_archive_order":23,"of":25,"metrics":{"Inception score":"7.07"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.01691","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}