{"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/on-convergence-and-stability-of-gans","title":"On Convergence and Stability of GANs","arxiv_id":"1705.07215","date":"2017-05-19","proceeding":"ICLR 2018 1","authors":["Naveen Kodali","Jacob Abernethy","James Hays","Zsolt Kira"],"abstract":"We propose studying GAN training dynamics as regret minimization, which is in\ncontrast to the popular view that there is consistent minimization of a\ndivergence between real and generated distributions. We analyze the convergence\nof GAN training from this new point of view to understand why mode collapse\nhappens. We hypothesize the existence of undesirable local equilibria in this\nnon-convex game to be responsible for mode collapse. We observe that these\nlocal equilibria often exhibit sharp gradients of the discriminator function\naround some real data points. We demonstrate that these degenerate local\nequilibria can be avoided with a gradient penalty scheme called DRAGAN. We show\nthat DRAGAN enables faster training, achieves improved stability with fewer\nmode collapses, and leads to generator networks with better modeling\nperformance across a variety of architectures and objective functions.","url_abs":"http://arxiv.org/abs/1705.07215v5","url_pdf":"http://arxiv.org/pdf/1705.07215v5.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":"on-convergence-and-stability-of-gans","repo_url":"https://github.com/kodalinaveen3/DRAGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"on-convergence-and-stability-of-gans","repo_url":"https://github.com/LynnHo/DCGAN-LSGAN-WGAN-WGAN-GP-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"on-convergence-and-stability-of-gans","repo_url":"https://github.com/eriklindernoren/PyTorch-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"on-convergence-and-stability-of-gans","repo_url":"https://github.com/marload/GANs-TensorFlow2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"on-convergence-and-stability-of-gans","repo_url":"https://github.com/rohitpatwa/gans-mode-collapse","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"on-convergence-and-stability-of-gans","repo_url":"https://github.com/ydataai/ydata-synthetic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"on-convergence-and-stability-of-gans","repo_url":"https://github.com/zhengziqiang/ReshapeGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"on-convergence-and-stability-of-gans","repo_url":"https://github.com/ChristophReich1996/Dirac-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.07215","atlas_url":"https://app.syntology.ai/?focus=1705.07215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.07215"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ydataai/ydata-synthetic","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ChristophReich1996/Dirac-GAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rohitpatwa/gans-mode-collapse","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhengziqiang/ReshapeGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LynnHo/DCGAN-LSGAN-WGAN-WGAN-GP-Tensorflow","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kodalinaveen3/DRAGAN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eriklindernoren/PyTorch-GAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marload/GANs-TensorFlow2","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c0ef577ceff3d8e3","entry":"compute_gradient_penalty","repo":"eriklindernoren/PyTorch-GAN","repo_kind":"listed","path":"implementations/dragan/dragan.py","file_url":"https://github.com/eriklindernoren/PyTorch-GAN/blob/HEAD/implementations/dragan/dragan.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c0ef577ceff3d8e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}