{"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/being-robust-in-high-dimensions-can-be","title":"Being Robust (in High Dimensions) Can Be Practical","arxiv_id":"1703.00893","date":"2017-03-02","proceeding":"ICML 2017 8","authors":["Ilias Diakonikolas","Gautam Kamath","Daniel M. Kane","Jerry Li","Ankur Moitra","Alistair Stewart"],"abstract":"Robust estimation is much more challenging in high dimensions than it is in\none dimension: Most techniques either lead to intractable optimization problems\nor estimators that can tolerate only a tiny fraction of errors. Recent work in\ntheoretical computer science has shown that, in appropriate distributional\nmodels, it is possible to robustly estimate the mean and covariance with\npolynomial time algorithms that can tolerate a constant fraction of\ncorruptions, independent of the dimension. However, the sample and time\ncomplexity of these algorithms is prohibitively large for high-dimensional\napplications. In this work, we address both of these issues by establishing\nsample complexity bounds that are optimal, up to logarithmic factors, as well\nas giving various refinements that allow the algorithms to tolerate a much\nlarger fraction of corruptions. Finally, we show on both synthetic and real\ndata that our algorithms have state-of-the-art performance and suddenly make\nhigh-dimensional robust estimation a realistic possibility.","url_abs":"http://arxiv.org/abs/1703.00893v4","url_pdf":"http://arxiv.org/pdf/1703.00893v4.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":"being-robust-in-high-dimensions-can-be","repo_url":"https://github.com/hoonose/robust-filter","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"being-robust-in-high-dimensions-can-be","repo_url":"https://github.com/TurboFreeze/dp-robust-filter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1703.00893","atlas_url":"https://app.syntology.ai/?focus=1703.00893","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}