{"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/generalization-and-equilibrium-in-generative","title":"Generalization and Equilibrium in Generative Adversarial Nets (GANs)","arxiv_id":"1703.00573","date":"2017-03-02","proceeding":"ICML 2017 8","authors":["Sanjeev Arora","Rong Ge","YIngyu Liang","Tengyu Ma","Yi Zhang"],"abstract":"We show that training of generative adversarial network (GAN) may not have\ngood generalization properties; e.g., training may appear successful but the\ntrained distribution may be far from target distribution in standard metrics.\nHowever, generalization does occur for a weaker metric called neural net\ndistance. It is also shown that an approximate pure equilibrium exists in the\ndiscriminator/generator game for a special class of generators with natural\ntraining objectives when generator capacity and training set sizes are\nmoderate.\n  This existence of equilibrium inspires MIX+GAN protocol, which can be\ncombined with any existing GAN training, and empirically shown to improve some\nof them.","url_abs":"http://arxiv.org/abs/1703.00573v5","url_pdf":"http://arxiv.org/pdf/1703.00573v5.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":"generalization-and-equilibrium-in-generative","repo_url":"https://github.com/PrincetonML/MIX-plus-GANs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.00573","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}