{"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/hunting-for-discriminatory-proxies-in-linear","title":"Hunting for Discriminatory Proxies in Linear Regression Models","arxiv_id":"1810.07155","date":"2018-10-16","proceeding":"NeurIPS 2018 12","authors":["Samuel Yeom","Anupam Datta","Matt Fredrikson"],"abstract":"A machine learning model may exhibit discrimination when used to make\ndecisions involving people. One potential cause for such outcomes is that the\nmodel uses a statistical proxy for a protected demographic attribute. In this\npaper we formulate a definition of proxy use for the setting of linear\nregression and present algorithms for detecting proxies. Our definition follows\nrecent work on proxies in classification models, and characterizes a model's\nconstituent behavior that: 1) correlates closely with a protected random\nvariable, and 2) is causally influential in the overall behavior of the model.\nWe show that proxies in linear regression models can be efficiently identified\nby solving a second-order cone program, and further extend this result to\naccount for situations where the use of a certain input variable is justified\nas a `business necessity'. Finally, we present empirical results on two law\nenforcement datasets that exhibit varying degrees of racial disparity in\nprediction outcomes, demonstrating that proxies shed useful light on the causes\nof discriminatory behavior in models.","url_abs":"http://arxiv.org/abs/1810.07155v3","url_pdf":"http://arxiv.org/pdf/1810.07155v3.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":"hunting-for-discriminatory-proxies-in-linear","repo_url":"https://github.com/samuel-yeom/linreg-proxy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"linear-regression","method_name":"Linear Regression"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}