{"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/deep-knockoffs","title":"Deep Knockoffs","arxiv_id":"1811.06687","date":"2018-11-16","proceeding":null,"authors":["Yaniv Romano","Matteo Sesia","Emmanuel J. Candès"],"abstract":"This paper introduces a machine for sampling approximate model-X knockoffs\nfor arbitrary and unspecified data distributions using deep generative models.\nThe main idea is to iteratively refine a knockoff sampling mechanism until a\ncriterion measuring the validity of the produced knockoffs is optimized; this\ncriterion is inspired by the popular maximum mean discrepancy in machine\nlearning and can be thought of as measuring the distance to pairwise\nexchangeability between original and knockoff features. By building upon the\nexisting model-X framework, we thus obtain a flexible and model-free\nstatistical tool to perform controlled variable selection. Extensive numerical\nexperiments and quantitative tests confirm the generality, effectiveness, and\npower of our deep knockoff machines. Finally, we apply this new method to a\nreal study of mutations linked to changes in drug resistance in the human\nimmunodeficiency virus.","url_abs":"http://arxiv.org/abs/1811.06687v1","url_pdf":"http://arxiv.org/pdf/1811.06687v1.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":"deep-knockoffs","repo_url":"https://github.com/msesia/deepknockoffs","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-knockoffs","repo_url":"https://github.com/alec-flowers/machine-learning-cs433-p2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-knockoffs","repo_url":"https://github.com/patrickvossler18/dk_fork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"deep-knockoffs","repo_url":"https://github.com/peterpark77/deepknockoffs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"variable-selection","task_name":"Variable Selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.06687","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}