{"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/the-effects-of-overparameterization-on","title":"Critical Influence of Overparameterization on Sharpness-aware Minimization","arxiv_id":"2311.17539","date":"2023-11-29","proceeding":null,"authors":["Sungbin Shin","Dongyeop Lee","Maksym Andriushchenko","Namhoon Lee"],"abstract":"Sharpness-Aware Minimization (SAM) has attracted considerable attention for its effectiveness in improving generalization in deep neural network training by explicitly minimizing sharpness in the loss landscape. Its success, however, relies on the assumption that there exists sufficient variability of flatness in the solution space-a condition commonly facilitated by overparameterization. Yet, the interaction between SAM and overparameterization has not been thoroughly investigated, leaving a gap in understanding precisely how overparameterization affects SAM. Thus, in this work, we analyze SAM under varying degrees of overparameterization, presenting both empirical and theoretical findings that reveal its critical influence on SAM's effectiveness. First, we conduct extensive numerical experiments across diverse domains, demonstrating that SAM consistently benefits from overparameterization. Next, we attribute this phenomenon to the interplay between the enlarged solution space and increased implicit bias resulting from overparameterization. Furthermore, we show that this effect is particularly pronounced in practical settings involving label noise and sparsity, and yet, sufficient regularization is necessary. Last but not least, we provide other theoretical insights into how overparameterization helps SAM achieve minima with more uniform Hessian moments compared to SGD, and much faster convergence at a linear rate.","url_abs":"https://arxiv.org/abs/2311.17539v5","url_pdf":"https://arxiv.org/pdf/2311.17539v5.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":"the-effects-of-overparameterization-on","repo_url":"https://github.com/log-postech/sam-overparam","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"}],"methods":[{"method_slug":"sam","method_name":"SAM"},{"method_slug":"sgd","method_name":"SGD"},{"method_slug":"sharpness-aware-minimization","method_name":"Sharpness-Aware Minimization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.17539","atlas_url":"https://app.syntology.ai/?focus=2311.17539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17539"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/log-postech/sam-overparam","reach":{"status":"ok"}}],"summary":{"ran":5,"unverified":4},"by_repo_kind":{"official":{"samples":9,"ran":5,"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":9,"samples":[{"code_sha256_prefix":"c6e147fc2a71ea72","entry":"cifar10_augment","repo":"log-postech/sam-overparam","repo_kind":"official","path":"input_pipeline.py","file_url":"https://github.com/log-postech/sam-overparam/blob/HEAD/input_pipeline.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":"c6e147fc2a71ea72"}},{"code_sha256_prefix":"6f369ebdcbe5c0a3","entry":"cross_entropy_loss","repo":"log-postech/sam-overparam","repo_kind":"official","path":"train_utils.py","file_url":"https://github.com/log-postech/sam-overparam/blob/HEAD/train_utils.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":"6f369ebdcbe5c0a3"}},{"code_sha256_prefix":"7542a331d6feeafd","entry":"distorted_bounding_box_crop","repo":"log-postech/sam-overparam","repo_kind":"official","path":"input_pipeline.py","file_url":"https://github.com/log-postech/sam-overparam/blob/HEAD/input_pipeline.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":"7542a331d6feeafd"}},{"code_sha256_prefix":"70045adf02f53c3d","entry":"normalize_image","repo":"log-postech/sam-overparam","repo_kind":"official","path":"input_pipeline.py","file_url":"https://github.com/log-postech/sam-overparam/blob/HEAD/input_pipeline.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":"70045adf02f53c3d"}},{"code_sha256_prefix":"14f21bb3184fbb5b","entry":"random_score","repo":"log-postech/sam-overparam","repo_kind":"official","path":"pruner.py","file_url":"https://github.com/log-postech/sam-overparam/blob/HEAD/pruner.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":"14f21bb3184fbb5b"}},{"code_sha256_prefix":"2d37a890b45f92e7","entry":"compute_metrics","repo":"log-postech/sam-overparam","repo_kind":"official","path":"train_utils.py","file_url":"https://github.com/log-postech/sam-overparam/blob/HEAD/train_utils.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":"2d37a890b45f92e7"}},{"code_sha256_prefix":"db2c4f5af4c6f411","entry":"dual_vector","repo":"log-postech/sam-overparam","repo_kind":"official","path":"train_utils.py","file_url":"https://github.com/log-postech/sam-overparam/blob/HEAD/train_utils.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":"db2c4f5af4c6f411"}},{"code_sha256_prefix":"7b46e9fd8ddbc252","entry":"magnitude_score","repo":"log-postech/sam-overparam","repo_kind":"official","path":"pruner.py","file_url":"https://github.com/log-postech/sam-overparam/blob/HEAD/pruner.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":"7b46e9fd8ddbc252"}},{"code_sha256_prefix":"2bbb8e7b5d4d18c6","entry":"snip_score","repo":"log-postech/sam-overparam","repo_kind":"official","path":"pruner.py","file_url":"https://github.com/log-postech/sam-overparam/blob/HEAD/pruner.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":"2bbb8e7b5d4d18c6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}