{"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/towards-constituting-mathematical-structures","title":"Towards Constituting Mathematical Structures for Learning to Optimize","arxiv_id":"2305.18577","date":"2023-05-29","proceeding":null,"authors":["Jialin Liu","Xiaohan Chen","Zhangyang Wang","Wotao Yin","HanQin Cai"],"abstract":"Learning to Optimize (L2O), a technique that utilizes machine learning to learn an optimization algorithm automatically from data, has gained arising attention in recent years. A generic L2O approach parameterizes the iterative update rule and learns the update direction as a black-box network. While the generic approach is widely applicable, the learned model can overfit and may not generalize well to out-of-distribution test sets. In this paper, we derive the basic mathematical conditions that successful update rules commonly satisfy. Consequently, we propose a novel L2O model with a mathematics-inspired structure that is broadly applicable and generalized well to out-of-distribution problems. Numerical simulations validate our theoretical findings and demonstrate the superior empirical performance of the proposed L2O model.","url_abs":"https://arxiv.org/abs/2305.18577v1","url_pdf":"https://arxiv.org/pdf/2305.18577v1.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":"towards-constituting-mathematical-structures","repo_url":"https://github.com/xhchrn/ms4l2o","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.18577","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18577"}},"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":"deterministic:regex_extraction","url":"https://github.com/xhchrn/MS4L2O","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xhchrn/ms4l2o","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":1,"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":"70c15547a7bf67f1","entry":"shrink","repo":"xhchrn/MS4L2O","repo_kind":"official","path":"optimizers/ada_lista.py","file_url":"https://github.com/xhchrn/MS4L2O/blob/HEAD/optimizers/ada_lista.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"70c15547a7bf67f1"}},{"code_sha256_prefix":"ed20c876e8874e05","entry":"CoordMathLSTM","repo":"xhchrn/ms4l2o","repo_kind":"official","path":"optimizers/coord_math_lstm.py","file_url":"https://github.com/xhchrn/ms4l2o/blob/HEAD/optimizers/coord_math_lstm.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":"ed20c876e8874e05"}},{"code_sha256_prefix":"46e93e3246c6c5ec","entry":"make_train_step","repo":"xhchrn/MS4L2O","repo_kind":"official","path":"main_unroll.py","file_url":"https://github.com/xhchrn/MS4L2O/blob/HEAD/main_unroll.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":"46e93e3246c6c5ec"}},{"code_sha256_prefix":"fc1dc877fddc1718","entry":"normalize_data","repo":"xhchrn/MS4L2O","repo_kind":"official","path":"optimizees/logistic_real_data.py","file_url":"https://github.com/xhchrn/MS4L2O/blob/HEAD/optimizees/logistic_real_data.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":"fc1dc877fddc1718"}},{"code_sha256_prefix":"e913750552632f7a","entry":"setup_logger","repo":"xhchrn/MS4L2O","repo_kind":"official","path":"utils.py","file_url":"https://github.com/xhchrn/MS4L2O/blob/HEAD/utils.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":"e913750552632f7a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}