{"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/improved-svrg-for-non-strongly-convex-or-sum","title":"Improved SVRG for Non-Strongly-Convex or Sum-of-Non-Convex Objectives","arxiv_id":"1506.01972","date":"2015-06-05","proceeding":null,"authors":["Zeyuan Allen-Zhu","Yang Yuan"],"abstract":"Many classical algorithms are found until several years later to outlive the\nconfines in which they were conceived, and continue to be relevant in\nunforeseen settings. In this paper, we show that SVRG is one such method: being\noriginally designed for strongly convex objectives, it is also very robust in\nnon-strongly convex or sum-of-non-convex settings.\n  More precisely, we provide new analysis to improve the state-of-the-art\nrunning times in both settings by either applying SVRG or its novel variant.\nSince non-strongly convex objectives include important examples such as Lasso\nor logistic regression, and sum-of-non-convex objectives include famous\nexamples such as stochastic PCA and is even believed to be related to training\ndeep neural nets, our results also imply better performances in these\napplications.","url_abs":"http://arxiv.org/abs/1506.01972v3","url_pdf":"http://arxiv.org/pdf/1506.01972v3.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":"improved-svrg-for-non-strongly-convex-or-sum","repo_url":"https://github.com/kul-forbes/CIAOAlgorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"improved-svrg-for-non-strongly-convex-or-sum","repo_url":"https://github.com/kul-forbes/CIAOAlgorithms.jl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"improved-svrg-for-non-strongly-convex-or-sum","repo_url":"https://github.com/kul-optec/CIAOAlgorithms.jl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"pca","method_name":"PCA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1506.01972","atlas_url":"https://app.syntology.ai/?focus=1506.01972","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}