{"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/gan-qp-a-novel-gan-framework-without-gradient","title":"GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint","arxiv_id":"1811.07296","date":"2018-11-18","proceeding":null,"authors":["Jianlin Su"],"abstract":"We know SGAN may have a risk of gradient vanishing. A significant improvement\nis WGAN, with the help of 1-Lipschitz constraint on discriminator to prevent\nfrom gradient vanishing. Is there any GAN having no gradient vanishing and no\n1-Lipschitz constraint on discriminator? We do find one, called GAN-QP.\n  To construct a new framework of Generative Adversarial Network (GAN) usually\nincludes three steps: 1. choose a probability divergence; 2. convert it into a\ndual form; 3. play a min-max game. In this articles, we demonstrate that the\nfirst step is not necessary. We can analyse the property of divergence and even\nconstruct new divergence in dual space directly. As a reward, we obtain a\nsimpler alternative of WGAN: GAN-QP. We demonstrate that GAN-QP have a better\nperformance than WGAN in theory and practice.","url_abs":"http://arxiv.org/abs/1811.07296v4","url_pdf":"http://arxiv.org/pdf/1811.07296v4.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":"gan-qp-a-novel-gan-framework-without-gradient","repo_url":"https://github.com/bojone/gan-qp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"gan-qp-a-novel-gan-framework-without-gradient","repo_url":"https://github.com/One-sixth/gan-qp-mod-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"gan-qp-a-novel-gan-framework-without-gradient","repo_url":"https://github.com/createamind/VDB-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"gan-qp-a-novel-gan-framework-without-gradient","repo_url":"https://github.com/rahulbhalley/gan-qp.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":null,"task_name":"Generative Adversarial Network"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"wgan","method_name":"WGAN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1811.07296","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}