{"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/sassha-sharpness-aware-adaptive-second-order","title":"SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation","arxiv_id":"2502.18153","date":"2025-02-25","proceeding":null,"authors":["Dahun Shin","Dongyeop Lee","Jinseok Chung","Namhoon Lee"],"abstract":"Approximate second-order optimization methods often exhibit poorer generalization compared to first-order approaches. In this work, we look into this issue through the lens of the loss landscape and find that existing second-order methods tend to converge to sharper minima compared to SGD. In response, we propose Sassha, a novel second-order method designed to enhance generalization by explicitly reducing sharpness of the solution, while stabilizing the computation of approximate Hessians along the optimization trajectory. In fact, this sharpness minimization scheme is crafted also to accommodate lazy Hessian updates, so as to secure efficiency besides flatness. To validate its effectiveness, we conduct a wide range of standard deep learning experiments where Sassha demonstrates its outstanding generalization performance that is comparable to, and mostly better than, other methods. We provide a comprehensive set of analyses including convergence, robustness, stability, efficiency, and cost.","url_abs":"https://arxiv.org/abs/2502.18153v1","url_pdf":"https://arxiv.org/pdf/2502.18153v1.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":"sassha-sharpness-aware-adaptive-second-order","repo_url":"https://github.com/LOG-postech/Sassha","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"second-order-methods","task_name":"Second-order methods"}],"methods":[{"method_slug":"set","method_name":"SET"},{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.18153","atlas_url":"https://app.syntology.ai/?focus=2502.18153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18153"}},"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":"deterministic:regex_extraction","url":"https://github.com/LOG-postech/Sassha","reach":null}],"summary":{"ran":1,"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"6e905f73ff60456b","entry":"SASSHA","repo":"LOG-postech/Sassha","repo_kind":"official","path":"optimizers/sassha.py","file_url":"https://github.com/LOG-postech/Sassha/blob/HEAD/optimizers/sassha.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":"6e905f73ff60456b"}},{"code_sha256_prefix":"ef298ecd9f6a7cc0","entry":"get_lr","repo":"log-postech/sassha","repo_kind":"official","path":"pretraining/train_sassha.py","file_url":"https://github.com/log-postech/sassha/blob/HEAD/pretraining/train_sassha.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ef298ecd9f6a7cc0"}},{"code_sha256_prefix":"60d8a51f8df8518d","entry":"maybe_no_sync","repo":"log-postech/sassha","repo_kind":"official","path":"pretraining/train_sassha.py","file_url":"https://github.com/log-postech/sassha/blob/HEAD/pretraining/train_sassha.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"60d8a51f8df8518d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}