{"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/greedy-step-averaging-a-parameter-free","title":"Greedy Step Averaging: A parameter-free stochastic optimization method","arxiv_id":"1611.03608","date":"2016-11-11","proceeding":null,"authors":["Xiatian Zhang","Fan Yao","Yongjun Tian"],"abstract":"In this paper we present the greedy step averaging(GSA) method, a\nparameter-free stochastic optimization algorithm for a variety of machine\nlearning problems. As a gradient-based optimization method, GSA makes use of\nthe information from the minimizer of a single sample's loss function, and\ntakes average strategy to calculate reasonable learning rate sequence. While\nmost existing gradient-based algorithms introduce an increasing number of hyper\nparameters or try to make a trade-off between computational cost and\nconvergence rate, GSA avoids the manual tuning of learning rate and brings in\nno more hyper parameters or extra cost. We perform exhaustive numerical\nexperiments for logistic and softmax regression to compare our method with the\nother state of the art ones on 16 datasets. Results show that GSA is robust on\nvarious scenarios.","url_abs":"http://arxiv.org/abs/1611.03608v1","url_pdf":"http://arxiv.org/pdf/1611.03608v1.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":"greedy-step-averaging-a-parameter-free","repo_url":"https://github.com/TalkingData/Fregata","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}