{"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/stochastic-conjugate-gradient-algorithm-with","title":"Stochastic Conjugate Gradient Algorithm with Variance Reduction","arxiv_id":"1710.09979","date":"2017-10-27","proceeding":null,"authors":["Xiao-Bo Jin","Xu-Yao Zhang","Kai-Zhu Huang","Guang-Gang Geng"],"abstract":"Conjugate gradient (CG) methods are a class of important methods for solving\nlinear equations and nonlinear optimization problems. In this paper, we propose\na new stochastic CG algorithm with variance reduction and we prove its linear\nconvergence with the Fletcher and Reeves method for strongly convex and smooth\nfunctions. We experimentally demonstrate that the CG with variance reduction\nalgorithm converges faster than its counterparts for four learning models,\nwhich may be convex, nonconvex or nonsmooth. In addition, its area under the\ncurve performance on six large-scale data sets is comparable to that of the\nLIBLINEAR solver for the L2-regularized L2-loss but with a significant\nimprovement in computational efficiency","url_abs":"http://arxiv.org/abs/1710.09979v2","url_pdf":"http://arxiv.org/pdf/1710.09979v2.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":"stochastic-conjugate-gradient-algorithm-with","repo_url":"https://github.com/xbjin/cgvr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}