{"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/second-order-stochastic-optimization-for","title":"Second-Order Stochastic Optimization for Machine Learning in Linear Time","arxiv_id":"1602.03943","date":"2016-02-12","proceeding":null,"authors":["Naman Agarwal","Brian Bullins","Elad Hazan"],"abstract":"First-order stochastic methods are the state-of-the-art in large-scale\nmachine learning optimization owing to efficient per-iteration complexity.\nSecond-order methods, while able to provide faster convergence, have been much\nless explored due to the high cost of computing the second-order information.\nIn this paper we develop second-order stochastic methods for optimization\nproblems in machine learning that match the per-iteration cost of gradient\nbased methods, and in certain settings improve upon the overall running time\nover popular first-order methods. Furthermore, our algorithm has the desirable\nproperty of being implementable in time linear in the sparsity of the input\ndata.","url_abs":"http://arxiv.org/abs/1602.03943v5","url_pdf":"http://arxiv.org/pdf/1602.03943v5.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":"second-order-stochastic-optimization-for","repo_url":"https://github.com/brianbullins/lissa_code","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"second-order-stochastic-optimization-for","repo_url":"https://github.com/alstonlo/torch-influence","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"second-order-stochastic-optimization-for","repo_url":"https://github.com/darkonhub/darkon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"second-order-stochastic-optimization-for","repo_url":"https://github.com/aai-institute/pyDVL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"LGPL-3.0"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"second-order-methods","task_name":"Second-order methods"},{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1602.03943","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}