{"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/second-moment-loss-a-novel-regression-1","title":"Wasserstein Dropout","arxiv_id":"2012.12687","date":"2020-12-23","proceeding":null,"authors":["Joachim Sicking","Maram Akila","Maximilian Pintz","Tim Wirtz","Asja Fischer","Stefan Wrobel"],"abstract":"Despite of its importance for safe machine learning, uncertainty quantification for neural networks is far from being solved. State-of-the-art approaches to estimate neural uncertainties are often hybrid, combining parametric models with explicit or implicit (dropout-based) ensembling. We take another pathway and propose a novel approach to uncertainty quantification for regression tasks, Wasserstein dropout, that is purely non-parametric. Technically, it captures aleatoric uncertainty by means of dropout-based sub-network distributions. This is accomplished by a new objective which minimizes the Wasserstein distance between the label distribution and the model distribution. An extensive empirical analysis shows that Wasserstein dropout outperforms state-of-the-art methods, on vanilla test data as well as under distributional shift, in terms of producing more accurate and stable uncertainty estimates.","url_abs":"https://arxiv.org/abs/2012.12687v2","url_pdf":"https://arxiv.org/pdf/2012.12687v2.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":"second-moment-loss-a-novel-regression-1","repo_url":"https://github.com/fraunhofer-iais/second-moment-loss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.12687","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}