{"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/alice-towards-understanding-adversarial","title":"ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching","arxiv_id":"1709.01215","date":"2017-09-05","proceeding":"NeurIPS 2017 12","authors":["Chunyuan Li","Hao liu","Changyou Chen","Yunchen Pu","Liqun Chen","Ricardo Henao","Lawrence Carin"],"abstract":"We investigate the non-identifiability issues associated with bidirectional\nadversarial training for joint distribution matching. Within a framework of\nconditional entropy, we propose both adversarial and non-adversarial approaches\nto learn desirable matched joint distributions for unsupervised and supervised\ntasks. We unify a broad family of adversarial models as joint distribution\nmatching problems. Our approach stabilizes learning of unsupervised\nbidirectional adversarial learning methods. Further, we introduce an extension\nfor semi-supervised learning tasks. Theoretical results are validated in\nsynthetic data and real-world applications.","url_abs":"http://arxiv.org/abs/1709.01215v2","url_pdf":"http://arxiv.org/pdf/1709.01215v2.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":"alice-towards-understanding-adversarial","repo_url":"https://github.com/ChunyuanLI/ALICE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"alice-towards-understanding-adversarial","repo_url":"https://github.com/ChunyuanLI/MNIST_Inception_Score","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"alice-towards-understanding-adversarial","repo_url":"https://github.com/FilLTP89/SeismoALICE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"alice-towards-understanding-adversarial","repo_url":"https://github.com/weituo12321/PREVALENT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"alice-towards-understanding-adversarial","repo_url":"https://github.com/zhenxuan00/graphical-gan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.01215","atlas_url":"https://app.syntology.ai/?focus=1709.01215","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}