{"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/stabilizing-training-of-generative","title":"Stabilizing Training of Generative Adversarial Networks through Regularization","arxiv_id":"1705.09367","date":"2017-05-25","proceeding":"NeurIPS 2017 12","authors":["Kevin Roth","Aurelien Lucchi","Sebastian Nowozin","Thomas Hofmann"],"abstract":"Deep generative models based on Generative Adversarial Networks (GANs) have\ndemonstrated impressive sample quality but in order to work they require a\ncareful choice of architecture, parameter initialization, and selection of\nhyper-parameters. This fragility is in part due to a dimensional mismatch or\nnon-overlapping support between the model distribution and the data\ndistribution, causing their density ratio and the associated f-divergence to be\nundefined. We overcome this fundamental limitation and propose a new\nregularization approach with low computational cost that yields a stable GAN\ntraining procedure. We demonstrate the effectiveness of this regularizer across\nseveral architectures trained on common benchmark image generation tasks. Our\nregularization turns GAN models into reliable building blocks for deep\nlearning.","url_abs":"http://arxiv.org/abs/1705.09367v2","url_pdf":"http://arxiv.org/pdf/1705.09367v2.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":"stabilizing-training-of-generative","repo_url":"https://github.com/rothk/Stabilizing_GANs","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":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.09367","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}