{"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/learning-to-pivot-with-adversarial-networks","title":"Learning to Pivot with Adversarial Networks","arxiv_id":"1611.01046","date":"2016-11-03","proceeding":"NeurIPS 2017 12","authors":["Gilles Louppe","Michael Kagan","Kyle Cranmer"],"abstract":"Several techniques for domain adaptation have been proposed to account for\ndifferences in the distribution of the data used for training and testing. The\nmajority of this work focuses on a binary domain label. Similar problems occur\nin a scientific context where there may be a continuous family of plausible\ndata generation processes associated to the presence of systematic\nuncertainties. Robust inference is possible if it is based on a pivot -- a\nquantity whose distribution does not depend on the unknown values of the\nnuisance parameters that parametrize this family of data generation processes.\nIn this work, we introduce and derive theoretical results for a training\nprocedure based on adversarial networks for enforcing the pivotal property (or,\nequivalently, fairness with respect to continuous attributes) on a predictive\nmodel. The method includes a hyperparameter to control the trade-off between\naccuracy and robustness. We demonstrate the effectiveness of this approach with\na toy example and examples from particle physics.","url_abs":"http://arxiv.org/abs/1611.01046v3","url_pdf":"http://arxiv.org/pdf/1611.01046v3.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":"learning-to-pivot-with-adversarial-networks","repo_url":"https://github.com/Nellaker-group/FairUnsupervisedRepresentations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-to-pivot-with-adversarial-networks","repo_url":"https://github.com/faroukmokhtar/DESY","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-pivot-with-adversarial-networks","repo_url":"https://github.com/faroukmokhtar/DESYproject","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-pivot-with-adversarial-networks","repo_url":"https://github.com/faroukmokhtar/GradProject","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-pivot-with-adversarial-networks","repo_url":"https://github.com/glouppe/paper-learning-to-pivot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"fairness","task_name":"Fairness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.01046","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}