{"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/how-sgd-selects-the-global-minima-in-over","title":"How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective","arxiv_id":null,"date":"2018-12-01","proceeding":"NeurIPS 2018 12","authors":["Lei Wu","Chao Ma","Weinan E"],"abstract":"The question of which global minima are accessible by a stochastic gradient decent (SGD)  algorithm with specific learning rate and batch size is studied from the perspective of dynamical stability.  The concept of non-uniformity is introduced, which, together with sharpness, characterizes the stability property of a global minimum and hence the accessibility of a particular SGD algorithm to that global minimum. In particular, this analysis shows that  learning rate and batch size play different roles in minima selection.  Extensive empirical results seem to correlate well with the theoretical findings and provide further support to these  claims.","url_abs":"http://papers.nips.cc/paper/8049-how-sgd-selects-the-global-minima-in-over-parameterized-learning-a-dynamical-stability-perspective","url_pdf":"http://papers.nips.cc/paper/8049-how-sgd-selects-the-global-minima-in-over-parameterized-learning-a-dynamical-stability-perspective.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":"how-sgd-selects-the-global-minima-in-over","repo_url":"https://github.com/leiwu1990/sgd.stability","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}