{"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/generalization-properties-and-implicit","title":"Generalization Properties and Implicit Regularization for Multiple Passes SGM","arxiv_id":"1605.08375","date":"2016-05-26","proceeding":null,"authors":["Junhong Lin","Raffaello Camoriano","Lorenzo Rosasco"],"abstract":"We study the generalization properties of stochastic gradient methods for\nlearning with convex loss functions and linearly parameterized functions. We\nshow that, in the absence of penalizations or constraints, the stability and\napproximation properties of the algorithm can be controlled by tuning either\nthe step-size or the number of passes over the data. In this view, these\nparameters can be seen to control a form of implicit regularization. Numerical\nresults complement the theoretical findings.","url_abs":"http://arxiv.org/abs/1605.08375v1","url_pdf":"http://arxiv.org/pdf/1605.08375v1.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":"generalization-properties-and-implicit","repo_url":"https://github.com/Adeikalam/Generalization-Properties-of-Algorithms-in-ML","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1605.08375","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}