{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/coulomb-gans-provably-optimal-nash-equilibria","title":"Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields","arxiv_id":"1708.08819","date":"2017-08-29","proceeding":"ICLR 2018 1","authors":["Thomas Unterthiner","Bernhard Nessler","Calvin Seward","Günter Klambauer","Martin Heusel","Hubert Ramsauer","Sepp Hochreiter"],"abstract":"Generative adversarial networks (GANs) evolved into one of the most\nsuccessful unsupervised techniques for generating realistic images. Even though\nit has recently been shown that GAN training converges, GAN models often end up\nin local Nash equilibria that are associated with mode collapse or otherwise\nfail to model the target distribution. We introduce Coulomb GANs, which pose\nthe GAN learning problem as a potential field of charged particles, where\ngenerated samples are attracted to training set samples but repel each other.\nThe discriminator learns a potential field while the generator decreases the\nenergy by moving its samples along the vector (force) field determined by the\ngradient of the potential field. Through decreasing the energy, the GAN model\nlearns to generate samples according to the whole target distribution and does\nnot only cover some of its modes. We prove that Coulomb GANs possess only one\nNash equilibrium which is optimal in the sense that the model distribution\nequals the target distribution. We show the efficacy of Coulomb GANs on a\nvariety of image datasets. On LSUN and celebA, Coulomb GANs set a new state of\nthe art and produce a previously unseen variety of different samples.","url_abs":"http://arxiv.org/abs/1708.08819v3","url_pdf":"http://arxiv.org/pdf/1708.08819v3.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":"coulomb-gans-provably-optimal-nash-equilibria","repo_url":"https://github.com/bioinf-jku/coulomb_gan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1708.08819","atlas_url":"https://app.syntology.ai/?focus=1708.08819","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1708.08819"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1708.08819\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1708.08819"},"call":"get_concepts_for_paper(arxiv_id=\"1708.08819\")"}],"by_repo":[{"repo":"bioinf-jku/coulomb_gan","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b770c56e56afc89579b2cb3f0d2063dc7534847b3b41b1e5fa2ad8c27d3535fb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}