{"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/magan-margin-adaptation-for-generative","title":"MAGAN: Margin Adaptation for Generative Adversarial Networks","arxiv_id":"1704.03817","date":"2017-04-12","proceeding":null,"authors":["Ruohan Wang","Antoine Cully","Hyung Jin Chang","Yiannis Demiris"],"abstract":"We propose the Margin Adaptation for Generative Adversarial Networks (MAGANs)\nalgorithm, a novel training procedure for GANs to improve stability and\nperformance by using an adaptive hinge loss function. We estimate the\nappropriate hinge loss margin with the expected energy of the target\ndistribution, and derive principled criteria for when to update the margin. We\nprove that our method converges to its global optimum under certain\nassumptions. Evaluated on the task of unsupervised image generation, the\nproposed training procedure is simple yet robust on a diverse set of data, and\nachieves qualitative and quantitative improvements compared to the\nstate-of-the-art.","url_abs":"http://arxiv.org/abs/1704.03817v3","url_pdf":"http://arxiv.org/pdf/1704.03817v3.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":"magan-margin-adaptation-for-generative","repo_url":"https://github.com/RuohanW/magan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.03817","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}