{"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/not-so-random-features","title":"Not-So-Random Features","arxiv_id":"1710.10230","date":"2017-10-27","proceeding":"ICLR 2018 1","authors":["Brian Bullins","Cyril Zhang","Yi Zhang"],"abstract":"We propose a principled method for kernel learning, which relies on a\nFourier-analytic characterization of translation-invariant or\nrotation-invariant kernels. Our method produces a sequence of feature maps,\niteratively refining the SVM margin. We provide rigorous guarantees for\noptimality and generalization, interpreting our algorithm as online\nequilibrium-finding dynamics in a certain two-player min-max game. Evaluations\non synthetic and real-world datasets demonstrate scalability and consistent\nimprovements over related random features-based methods.","url_abs":"http://arxiv.org/abs/1710.10230v2","url_pdf":"http://arxiv.org/pdf/1710.10230v2.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":"not-so-random-features","repo_url":"https://github.com/yz-ignescent/Not-So-Random-Features","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1710.10230","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}