{"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/the-unreasonable-effectiveness-of-structured","title":"The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings","arxiv_id":"1703.00864","date":"2017-03-02","proceeding":"NeurIPS 2017 12","authors":["Krzysztof Choromanski","Mark Rowland","Adrian Weller"],"abstract":"We examine a class of embeddings based on structured random matrices with\northogonal rows which can be applied in many machine learning applications\nincluding dimensionality reduction and kernel approximation. For both the\nJohnson-Lindenstrauss transform and the angular kernel, we show that we can\nselect matrices yielding guaranteed improved performance in accuracy and/or\nspeed compared to earlier methods. We introduce matrices with complex entries\nwhich give significant further accuracy improvement. We provide geometric and\nMarkov chain-based perspectives to help understand the benefits, and empirical\nresults which suggest that the approach is helpful in a wider range of\napplications.","url_abs":"http://arxiv.org/abs/1703.00864v5","url_pdf":"http://arxiv.org/pdf/1703.00864v5.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":"the-unreasonable-effectiveness-of-structured","repo_url":"https://github.com/dnbaker/frp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"the-unreasonable-effectiveness-of-structured","repo_url":"https://github.com/joneswack/dp-rfs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.00864","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}