{"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/enhancing-sharpness-aware-optimization","title":"Enhancing Sharpness-Aware Optimization Through Variance Suppression","arxiv_id":"2309.15639","date":"2023-09-27","proceeding":"NeurIPS 2023 11","authors":["Bingcong Li","Georgios B. Giannakis"],"abstract":"Sharpness-aware minimization (SAM) has well documented merits in enhancing generalization of deep neural networks, even without sizable data augmentation. Embracing the geometry of the loss function, where neighborhoods of 'flat minima' heighten generalization ability, SAM seeks 'flat valleys' by minimizing the maximum loss caused by an adversary perturbing parameters within the neighborhood. Although critical to account for sharpness of the loss function, such an 'over-friendly adversary' can curtail the outmost level of generalization. The novel approach of this contribution fosters stabilization of adversaries through variance suppression (VaSSO) to avoid such friendliness. VaSSO's provable stability safeguards its numerical improvement over SAM in model-agnostic tasks, including image classification and machine translation. In addition, experiments confirm that VaSSO endows SAM with robustness against high levels of label noise.","url_abs":"https://arxiv.org/abs/2309.15639v3","url_pdf":"https://arxiv.org/pdf/2309.15639v3.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":"enhancing-sharpness-aware-optimization","repo_url":"https://github.com/bingcongli/vasso","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"sam","method_name":"SAM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.15639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15639"}},"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/bingcongli/vasso","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"09b3eb1183605360","entry":"accuracy","repo":"bingcongli/vasso","repo_kind":"official","path":"utils/engine.py","file_url":"https://github.com/bingcongli/vasso/blob/HEAD/utils/engine.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"09b3eb1183605360"}},{"code_sha256_prefix":"5045fff9712deacb","entry":"is_main_process","repo":"bingcongli/vasso","repo_kind":"official","path":"utils/dist.py","file_url":"https://github.com/bingcongli/vasso/blob/HEAD/utils/dist.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5045fff9712deacb"}},{"code_sha256_prefix":"3068ed82cef91c51","entry":"make_layers","repo":"bingcongli/vasso","repo_kind":"official","path":"models/vgg.py","file_url":"https://github.com/bingcongli/vasso/blob/HEAD/models/vgg.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3068ed82cef91c51"}},{"code_sha256_prefix":"58fa58169c5d0ed0","entry":"build_base_optimizer","repo":"bingcongli/vasso","repo_kind":"official","path":"solver/build.py","file_url":"https://github.com/bingcongli/vasso/blob/HEAD/solver/build.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58fa58169c5d0ed0"}},{"code_sha256_prefix":"c2aae7f983c0210a","entry":"configurable","repo":"bingcongli/vasso","repo_kind":"official","path":"utils/configurable.py","file_url":"https://github.com/bingcongli/vasso/blob/HEAD/utils/configurable.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c2aae7f983c0210a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}