{"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-the-regularization-of-wasserstein-gans","title":"On the regularization of Wasserstein GANs","arxiv_id":"1709.08894","date":"2017-09-26","proceeding":"ICLR 2018 1","authors":["Henning Petzka","Asja Fischer","Denis Lukovnicov"],"abstract":"Since their invention, generative adversarial networks (GANs) have become a\npopular approach for learning to model a distribution of real (unlabeled) data.\nConvergence problems during training are overcome by Wasserstein GANs which\nminimize the distance between the model and the empirical distribution in terms\nof a different metric, but thereby introduce a Lipschitz constraint into the\noptimization problem. A simple way to enforce the Lipschitz constraint on the\nclass of functions, which can be modeled by the neural network, is weight\nclipping. It was proposed that training can be improved by instead augmenting\nthe loss by a regularization term that penalizes the deviation of the gradient\nof the critic (as a function of the network's input) from one. We present\ntheoretical arguments why using a weaker regularization term enforcing the\nLipschitz constraint is preferable. These arguments are supported by\nexperimental results on toy data sets.","url_abs":"http://arxiv.org/abs/1709.08894v2","url_pdf":"http://arxiv.org/pdf/1709.08894v2.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-the-regularization-of-wasserstein-gans","repo_url":"https://github.com/lukovnikov/improved_wgan_training","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"on-the-regularization-of-wasserstein-gans","repo_url":"https://github.com/mikigom/WGAN-LP-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.08894","atlas_url":"https://app.syntology.ai/?focus=1709.08894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.08894"}},"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/mikigom/WGAN-LP-tensorflow","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lukovnikov/improved_wgan_training","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"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":"60fae9e8ba4c816b","entry":"get_perbatuation_samples","repo":"mikigom/WGAN-LP-tensorflow","repo_kind":"listed","path":"reg_losses.py","file_url":"https://github.com/mikigom/WGAN-LP-tensorflow/blob/HEAD/reg_losses.py","link_basis":"harvester_set","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":"60fae9e8ba4c816b"}},{"code_sha256_prefix":"b2af80daa00ecdbb","entry":"run","repo":"lukovnikov/improved_wgan_training","repo_kind":"official","path":"gan_toy.py","file_url":"https://github.com/lukovnikov/improved_wgan_training/blob/HEAD/gan_toy.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":"b2af80daa00ecdbb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}