{"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/improving-sam-requires-rethinking-its","title":"Improving SAM Requires Rethinking its Optimization Formulation","arxiv_id":"2407.12993","date":"2024-07-17","proceeding":null,"authors":["Wanyun Xie","Fabian Latorre","Kimon Antonakopoulos","Thomas Pethick","Volkan Cevher"],"abstract":"This paper rethinks Sharpness-Aware Minimization (SAM), which is originally formulated as a zero-sum game where the weights of a network and a bounded perturbation try to minimize/maximize, respectively, the same differentiable loss. To fundamentally improve this design, we argue that SAM should instead be reformulated using the 0-1 loss. As a continuous relaxation, we follow the simple conventional approach where the minimizing (maximizing) player uses an upper bound (lower bound) surrogate to the 0-1 loss. This leads to a novel formulation of SAM as a bilevel optimization problem, dubbed as BiSAM. BiSAM with newly designed lower-bound surrogate loss indeed constructs stronger perturbation. Through numerical evidence, we show that BiSAM consistently results in improved performance when compared to the original SAM and variants, while enjoying similar computational complexity. Our code is available at https://github.com/LIONS-EPFL/BiSAM.","url_abs":"https://arxiv.org/abs/2407.12993v1","url_pdf":"https://arxiv.org/pdf/2407.12993v1.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":"improving-sam-requires-rethinking-its","repo_url":"https://github.com/LIONS-EPFL/BiSAM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"bilevel-optimization","task_name":"Bilevel Optimization"}],"methods":[{"method_slug":"sam","method_name":"SAM"},{"method_slug":"sharpness-aware-minimization","method_name":"Sharpness-Aware Minimization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.12993","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12993"}},"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/LIONS-EPFL/BiSAM","reach":null}],"summary":{"ran":1,"ran_fixture":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"aacd1c60e21babdd","entry":"SAM","repo":"LIONS-EPFL/BiSAM","repo_kind":"official","path":"utility/sam.py","file_url":"https://github.com/LIONS-EPFL/BiSAM/blob/HEAD/utility/sam.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":"aacd1c60e21babdd"}},{"code_sha256_prefix":"83634a07e94d9e91","entry":"perturbation_loss_log","repo":"lions-epfl/bisam","repo_kind":"official","path":"loss_fnc.py","file_url":"https://github.com/lions-epfl/bisam/blob/HEAD/loss_fnc.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"83634a07e94d9e91"}},{"code_sha256_prefix":"dd73f8d81a55afb2","entry":"perturbation_loss_tanh","repo":"lions-epfl/bisam","repo_kind":"official","path":"loss_fnc.py","file_url":"https://github.com/lions-epfl/bisam/blob/HEAD/loss_fnc.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd73f8d81a55afb2"}},{"code_sha256_prefix":"e34a3257087e025a","entry":"smooth_crossentropy","repo":"lions-epfl/bisam","repo_kind":"official","path":"loss_fnc.py","file_url":"https://github.com/lions-epfl/bisam/blob/HEAD/loss_fnc.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e34a3257087e025a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}