{"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/unrolled-generative-adversarial-networks","title":"Unrolled Generative Adversarial Networks","arxiv_id":"1611.02163","date":"2016-11-07","proceeding":null,"authors":["Luke Metz","Ben Poole","David Pfau","Jascha Sohl-Dickstein"],"abstract":"We introduce a method to stabilize Generative Adversarial Networks (GANs) by\ndefining the generator objective with respect to an unrolled optimization of\nthe discriminator. This allows training to be adjusted between using the\noptimal discriminator in the generator's objective, which is ideal but\ninfeasible in practice, and using the current value of the discriminator, which\nis often unstable and leads to poor solutions. We show how this technique\nsolves the common problem of mode collapse, stabilizes training of GANs with\ncomplex recurrent generators, and increases diversity and coverage of the data\ndistribution by the generator.","url_abs":"http://arxiv.org/abs/1611.02163v4","url_pdf":"http://arxiv.org/pdf/1611.02163v4.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":"unrolled-generative-adversarial-networks","repo_url":"https://github.com/poolio/unrolled_gan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"unrolled-generative-adversarial-networks","repo_url":"https://github.com/MarisaKirisame/unroll_gan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"unrolled-generative-adversarial-networks","repo_url":"https://github.com/alex98chen/testGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"unrolled-generative-adversarial-networks","repo_url":"https://github.com/andrewliao11/unrolled-gans","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"unrolled-generative-adversarial-networks","repo_url":"https://github.com/apaszke/pytorch-dist","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"unrolled-generative-adversarial-networks","repo_url":"https://github.com/chameleonTK/continual-learning-for-HAR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"unrolled-generative-adversarial-networks","repo_url":"https://github.com/locuslab/gradient_regularized_gan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"unrolled-generative-adversarial-networks","repo_url":"https://github.com/lyken17/pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"unrolled-generative-adversarial-networks","repo_url":"https://github.com/mangoubi/Min-max-optimization-algorithm-for-training-GANs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"}],"methods":[],"datasets_introduced":[{"slug":"stacked-mnist","name":"Stacked MNIST","full_name":"Stacked MNIST"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.02163","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}