{"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/training-relu-networks-to-high-uniform","title":"Learning ReLU networks to high uniform accuracy is intractable","arxiv_id":"2205.13531","date":"2022-05-26","proceeding":null,"authors":["Julius Berner","Philipp Grohs","Felix Voigtlaender"],"abstract":"Statistical learning theory provides bounds on the necessary number of training samples needed to reach a prescribed accuracy in a learning problem formulated over a given target class. This accuracy is typically measured in terms of a generalization error, that is, an expected value of a given loss function. However, for several applications -- for example in a security-critical context or for problems in the computational sciences -- accuracy in this sense is not sufficient. In such cases, one would like to have guarantees for high accuracy on every input value, that is, with respect to the uniform norm. In this paper we precisely quantify the number of training samples needed for any conceivable training algorithm to guarantee a given uniform accuracy on any learning problem formulated over target classes containing (or consisting of) ReLU neural networks of a prescribed architecture. We prove that, under very general assumptions, the minimal number of training samples for this task scales exponentially both in the depth and the input dimension of the network architecture.","url_abs":"https://arxiv.org/abs/2205.13531v2","url_pdf":"https://arxiv.org/pdf/2205.13531v2.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":"training-relu-networks-to-high-uniform","repo_url":"https://github.com/juliusberner/theory2practice","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"learning-theory","task_name":"Learning Theory"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.13531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.13531"}},"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/juliusberner/theory2practice","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"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":"e92ca9ef7c125a4e","entry":"absolute_path","repo":"juliusberner/theory2practice","repo_kind":"official","path":"theory2practice/utils.py","file_url":"https://github.com/juliusberner/theory2practice/blob/HEAD/theory2practice/utils.py","link_basis":"harvester_set","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":"e92ca9ef7c125a4e"}},{"code_sha256_prefix":"aeee5d45a2d76e7f","entry":"default_config2name","repo":"juliusberner/theory2practice","repo_kind":"official","path":"theory2practice/analysis.py","file_url":"https://github.com/juliusberner/theory2practice/blob/HEAD/theory2practice/analysis.py","link_basis":"harvester_set","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":"aeee5d45a2d76e7f"}},{"code_sha256_prefix":"22aa73522242da0b","entry":"flatten","repo":"juliusberner/theory2practice","repo_kind":"official","path":"theory2practice/utils.py","file_url":"https://github.com/juliusberner/theory2practice/blob/HEAD/theory2practice/utils.py","link_basis":"harvester_set","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":"22aa73522242da0b"}},{"code_sha256_prefix":"22c9112cb21be04e","entry":"nested_get","repo":"juliusberner/theory2practice","repo_kind":"official","path":"theory2practice/utils.py","file_url":"https://github.com/juliusberner/theory2practice/blob/HEAD/theory2practice/utils.py","link_basis":"harvester_set","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":"22c9112cb21be04e"}},{"code_sha256_prefix":"055cc753611a64e8","entry":"restore_model","repo":"juliusberner/theory2practice","repo_kind":"official","path":"theory2practice/experiments.py","file_url":"https://github.com/juliusberner/theory2practice/blob/HEAD/theory2practice/experiments.py","link_basis":"harvester_set","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":"055cc753611a64e8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}