{"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/asynchronous-stochastic-convex-optimization","title":"Asynchronous stochastic convex optimization","arxiv_id":"1508.00882","date":"2015-08-04","proceeding":null,"authors":["John C. Duchi","Sorathan Chaturapruek","Christopher Ré"],"abstract":"We show that asymptotically, completely asynchronous stochastic gradient\nprocedures achieve optimal (even to constant factors) convergence rates for the\nsolution of convex optimization problems under nearly the same conditions\nrequired for asymptotic optimality of standard stochastic gradient procedures.\nRoughly, the noise inherent to the stochastic approximation scheme dominates\nany noise from asynchrony. We also give empirical evidence demonstrating the\nstrong performance of asynchronous, parallel stochastic optimization schemes,\ndemonstrating that the robustness inherent to stochastic approximation problems\nallows substantially faster parallel and asynchronous solution methods.","url_abs":"http://arxiv.org/abs/1508.00882v1","url_pdf":"http://arxiv.org/pdf/1508.00882v1.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":"asynchronous-stochastic-convex-optimization","repo_url":"https://worksheets.codalab.org/worksheets/0x610bcdb722bf48d3b537a65edf0fe72d","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1508.00882","atlas_url":"https://app.syntology.ai/?focus=1508.00882","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}