{"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/bridging-the-empirical-theoretical-gap-in","title":"Bridging the Empirical-Theoretical Gap in Neural Network Formal Language Learning Using Minimum Description Length","arxiv_id":"2402.10013","date":"2024-02-15","proceeding":null,"authors":["Nur Lan","Emmanuel Chemla","Roni Katzir"],"abstract":"Neural networks offer good approximation to many tasks but consistently fail to reach perfect generalization, even when theoretical work shows that such perfect solutions can be expressed by certain architectures. Using the task of formal language learning, we focus on one simple formal language and show that the theoretically correct solution is in fact not an optimum of commonly used objectives -- even with regularization techniques that according to common wisdom should lead to simple weights and good generalization (L1, L2) or other meta-heuristics (early-stopping, dropout). On the other hand, replacing standard targets with the Minimum Description Length objective (MDL) results in the correct solution being an optimum.","url_abs":"https://arxiv.org/abs/2402.10013v2","url_pdf":"https://arxiv.org/pdf/2402.10013v2.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":"bridging-the-empirical-theoretical-gap-in","repo_url":"https://github.com/0xnurl/mdl-lstm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.10013","atlas_url":"https://app.syntology.ai/?focus=2402.10013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10013"}},"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/0xnurl/mdl-lstm","reach":{"status":"ok"}}],"summary":{"ran":8,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":"b8b4484d54ea950b","entry":"get_dict_hash","repo":"0xnurl/mdl-lstm","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/0xnurl/mdl-lstm/blob/HEAD/src/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":"b8b4484d54ea950b"}},{"code_sha256_prefix":"6abd5d7bff7852e3","entry":"get_n_values_in_an_bn_corpus","repo":"0xnurl/mdl-lstm","repo_kind":"official","path":"src/corpora.py","file_url":"https://github.com/0xnurl/mdl-lstm/blob/HEAD/src/corpora.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":"6abd5d7bff7852e3"}},{"code_sha256_prefix":"bb86843196a4b8a8","entry":"get_net_device","repo":"0xnurl/mdl-lstm","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/0xnurl/mdl-lstm/blob/HEAD/src/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":"bb86843196a4b8a8"}},{"code_sha256_prefix":"bb33534fd5ff7586","entry":"is_masked","repo":"0xnurl/mdl-lstm","repo_kind":"official","path":"src/corpora.py","file_url":"https://github.com/0xnurl/mdl-lstm/blob/HEAD/src/corpora.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":"bb33534fd5ff7586"}},{"code_sha256_prefix":"f1acb7a1f4abfef1","entry":"make_an_bn_from_n_values","repo":"0xnurl/mdl-lstm","repo_kind":"official","path":"src/corpora.py","file_url":"https://github.com/0xnurl/mdl-lstm/blob/HEAD/src/corpora.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":"f1acb7a1f4abfef1"}},{"code_sha256_prefix":"9d64b8cd62852499","entry":"num_items_in_tensor","repo":"0xnurl/mdl-lstm","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/0xnurl/mdl-lstm/blob/HEAD/src/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":"9d64b8cd62852499"}},{"code_sha256_prefix":"61484adddf651bd0","entry":"pack_masked","repo":"0xnurl/mdl-lstm","repo_kind":"official","path":"src/networks.py","file_url":"https://github.com/0xnurl/mdl-lstm/blob/HEAD/src/networks.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":"61484adddf651bd0"}},{"code_sha256_prefix":"26986c3fdfcd580f","entry":"where_argbest","repo":"0xnurl/mdl-lstm","repo_kind":"official","path":"src/visualizations.py","file_url":"https://github.com/0xnurl/mdl-lstm/blob/HEAD/src/visualizations.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":"26986c3fdfcd580f"}},{"code_sha256_prefix":"6a12366d3aadc4eb","entry":"get_quantized_net","repo":"0xnurl/mdl-lstm","repo_kind":"official","path":"src/encoding.py","file_url":"https://github.com/0xnurl/mdl-lstm/blob/HEAD/src/encoding.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":"6a12366d3aadc4eb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}