{"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/adversarial-learning-of-a-sampler-based-on-an","title":"Adversarial Learning of a Sampler Based on an Unnormalized Distribution","arxiv_id":"1901.00612","date":"2019-01-03","proceeding":null,"authors":["Chunyuan Li","Ke Bai","Jianqiao Li","Guoyin Wang","Changyou Chen","Lawrence Carin"],"abstract":"We investigate adversarial learning in the case when only an unnormalized\nform of the density can be accessed, rather than samples. With insights so\ngarnered, adversarial learning is extended to the case for which one has access\nto an unnormalized form u(x) of the target density function, but no samples.\nFurther, new concepts in GAN regularization are developed, based on learning\nfrom samples or from u(x). The proposed method is compared to alternative\napproaches, with encouraging results demonstrated across a range of\napplications, including deep soft Q-learning.","url_abs":"http://arxiv.org/abs/1901.00612v1","url_pdf":"http://arxiv.org/pdf/1901.00612v1.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":"adversarial-learning-of-a-sampler-based-on-an","repo_url":"https://github.com/ChunyuanLI/RAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"adversarial-learning-of-a-sampler-based-on-an","repo_url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/ras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"adversarial-learning-of-a-sampler-based-on-an","repo_url":"https://github.com/code-implementation1/Code6/tree/main/ras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"form","task_name":"Form"},{"task_slug":"q-learning","task_name":"Q-Learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.00612","atlas_url":"https://app.syntology.ai/?focus=1901.00612","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}