{"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/minimum-sharpness-scale-invariant-parameter","title":"Minimum sharpness: Scale-invariant parameter-robustness of neural networks","arxiv_id":"2106.12612","date":"2021-06-23","proceeding":null,"authors":["Hikaru Ibayashi","Takuo Hamaguchi","Masaaki Imaizumi"],"abstract":"Toward achieving robust and defensive neural networks, the robustness against the weight parameters perturbations, i.e., sharpness, attracts attention in recent years (Sun et al., 2020). However, sharpness is known to remain a critical issue, \"scale-sensitivity.\" In this paper, we propose a novel sharpness measure, Minimum Sharpness. It is known that NNs have a specific scale transformation that constitutes equivalent classes where functional properties are completely identical, and at the same time, their sharpness could change unlimitedly. We define our sharpness through a minimization problem over the equivalent NNs being invariant to the scale transformation. We also develop an efficient and exact technique to make the sharpness tractable, which reduces the heavy computational costs involved with Hessian. In the experiment, we observed that our sharpness has a valid correlation with the generalization of NNs and runs with less computational cost than existing sharpness measures.","url_abs":"https://arxiv.org/abs/2106.12612v2","url_pdf":"https://arxiv.org/pdf/2106.12612v2.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":"minimum-sharpness-scale-invariant-parameter","repo_url":"https://github.com/ibayashi-hikaru/minimum-sharpness","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.12612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12612"}},"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/ibayashi-hikaru/minimum-sharpness","reach":null}],"summary":{"ran":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"803a7081ef5ab04f","entry":"LossFunctionOverAlpha","repo":"ibayashi-hikaru/minimum-sharpness","repo_kind":"official","path":"02-sharpness-comparison/experiment/sharpness/Minimum.py","file_url":"https://github.com/ibayashi-hikaru/minimum-sharpness/blob/HEAD/02-sharpness-comparison/experiment/sharpness/Minimum.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"803a7081ef5ab04f"}},{"code_sha256_prefix":"ae22aaba763f720b","entry":"_get_sharpness","repo":"ibayashi-hikaru/minimum-sharpness","repo_kind":"official","path":"02-sharpness-comparison/experiment/sharpness/Minimum.py","file_url":"https://github.com/ibayashi-hikaru/minimum-sharpness/blob/HEAD/02-sharpness-comparison/experiment/sharpness/Minimum.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ae22aaba763f720b"}},{"code_sha256_prefix":"8608526be377ff44","entry":"report","repo":"ibayashi-hikaru/minimum-sharpness","repo_kind":"official","path":"02-sharpness-comparison/experiment/sharpness/Minimum.py","file_url":"https://github.com/ibayashi-hikaru/minimum-sharpness/blob/HEAD/02-sharpness-comparison/experiment/sharpness/Minimum.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":"8608526be377ff44"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}