{"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/engineering-fast-multilevel-support-vector","title":"Engineering fast multilevel support vector machines","arxiv_id":"1707.07657","date":"2017-07-24","proceeding":null,"authors":["E. Sadrfaridpour","T. Razzaghi","I. Safro"],"abstract":"The computational complexity of solving nonlinear support vector machine\n(SVM) is prohibitive on large-scale data. In particular, this issue becomes\nvery sensitive when the data represents additional difficulties such as highly\nimbalanced class sizes. Typically, nonlinear kernels produce significantly\nhigher classification quality to linear kernels but introduce extra kernel and\nmodel parameters which requires computationally expensive fitting. This\nincreases the quality but also reduces the performance dramatically. We\nintroduce a generalized fast multilevel framework for regular and weighted SVM\nand discuss several versions of its algorithmic components that lead to a good\ntrade-off between quality and time. Our framework is implemented using PETSc\nwhich allows an easy integration with scientific computing tasks. The\nexperimental results demonstrate significant speed up compared to the\nstate-of-the-art nonlinear SVM libraries.\n  Reproducibility: our source code, documentation and parameters are available\nat https:// github.com/esadr/mlsvm.","url_abs":"http://arxiv.org/abs/1707.07657v3","url_pdf":"http://arxiv.org/pdf/1707.07657v3.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":"engineering-fast-multilevel-support-vector","repo_url":"https://github.com/esadr/mlsvm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}