{"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/towards-understanding-the-role-of-over","title":"Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks","arxiv_id":"1805.12076","date":"2018-05-30","proceeding":null,"authors":["Behnam Neyshabur","Zhiyuan Li","Srinadh Bhojanapalli","Yann Lecun","Nathan Srebro"],"abstract":"Despite existing work on ensuring generalization of neural networks in terms\nof scale sensitive complexity measures, such as norms, margin and sharpness,\nthese complexity measures do not offer an explanation of why neural networks\ngeneralize better with over-parametrization. In this work we suggest a novel\ncomplexity measure based on unit-wise capacities resulting in a tighter\ngeneralization bound for two layer ReLU networks. Our capacity bound correlates\nwith the behavior of test error with increasing network sizes, and could\npotentially explain the improvement in generalization with\nover-parametrization. We further present a matching lower bound for the\nRademacher complexity that improves over previous capacity lower bounds for\nneural networks.","url_abs":"http://arxiv.org/abs/1805.12076v1","url_pdf":"http://arxiv.org/pdf/1805.12076v1.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":"towards-understanding-the-role-of-over","repo_url":"https://github.com/bneyshabur/over-parametrization","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"towards-understanding-the-role-of-over","repo_url":"https://github.com/bneyshabur/generalization-bounds","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1805.12076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.12076"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bneyshabur/generalization-bounds","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bneyshabur/over-parametrization","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"eb36850fb9092242","entry":"calculate","repo":"bneyshabur/over-parametrization","repo_kind":"official","path":"measures.py","file_url":"https://github.com/bneyshabur/over-parametrization/blob/HEAD/measures.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb36850fb9092242"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}