{"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/falkon-an-optimal-large-scale-kernel-method","title":"FALKON: An Optimal Large Scale Kernel Method","arxiv_id":"1705.10958","date":"2017-05-31","proceeding":"NeurIPS 2017 12","authors":["Alessandro Rudi","Luigi Carratino","Lorenzo Rosasco"],"abstract":"Kernel methods provide a principled way to perform non linear, nonparametric\nlearning. They rely on solid functional analytic foundations and enjoy optimal\nstatistical properties. However, at least in their basic form, they have\nlimited applicability in large scale scenarios because of stringent\ncomputational requirements in terms of time and especially memory. In this\npaper, we take a substantial step in scaling up kernel methods, proposing\nFALKON, a novel algorithm that allows to efficiently process millions of\npoints. FALKON is derived combining several algorithmic principles, namely\nstochastic subsampling, iterative solvers and preconditioning. Our theoretical\nanalysis shows that optimal statistical accuracy is achieved requiring\nessentially $O(n)$ memory and $O(n\\sqrt{n})$ time. An extensive experimental\nanalysis on large scale datasets shows that, even with a single machine, FALKON\noutperforms previous state of the art solutions, which exploit\nparallel/distributed architectures.","url_abs":"http://arxiv.org/abs/1705.10958v3","url_pdf":"http://arxiv.org/pdf/1705.10958v3.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":"falkon-an-optimal-large-scale-kernel-method","repo_url":"https://github.com/LCSL/FALKON_paper","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"falkon-an-optimal-large-scale-kernel-method","repo_url":"https://github.com/enry12/FALKON","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"falkon-an-optimal-large-scale-kernel-method","repo_url":"https://github.com/enry12/SEMI-FALKON","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"falkon-an-optimal-large-scale-kernel-method","repo_url":"https://github.com/fwilliams/neural-splines","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.10958","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}