{"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/a-wasserstein-minimum-velocity-approach-to","title":"A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models","arxiv_id":"2002.07501","date":"2020-02-18","proceeding":"pproximateinference AABI Symposium 2019 12","authors":["Ziyu Wang","Shuyu Cheng","Yueru Li","Jun Zhu","Bo Zhang"],"abstract":"Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative. In this paper, we present a scalable approximation to a general family of learning objectives including score matching, by observing a new connection between these objectives and Wasserstein gradient flows. We present applications with promise in learning neural density estimators on manifolds, and training implicit variational and Wasserstein auto-encoders with a manifold-valued prior.","url_abs":"https://arxiv.org/abs/2002.07501v1","url_pdf":"https://arxiv.org/pdf/2002.07501v1.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":"a-wasserstein-minimum-velocity-approach-to","repo_url":"https://github.com/thu-ml/wmvl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.07501","atlas_url":"https://app.syntology.ai/?focus=2002.07501","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}