{"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-two-layer-relu-networks-with","title":"Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent","arxiv_id":"2002.04861","date":"2020-02-12","proceeding":null,"authors":["David Holzmüller","Ingo Steinwart"],"abstract":"We prove that two-layer (Leaky)ReLU networks initialized by e.g. the widely used method proposed by He et al. (2015) and trained using gradient descent on a least-squares loss are not universally consistent. Specifically, we describe a large class of one-dimensional data-generating distributions for which, with high probability, gradient descent only finds a bad local minimum of the optimization landscape, since it is unable to move the biases far away from their initialization at zero. It turns out that in these cases, the found network essentially performs linear regression even if the target function is non-linear. We further provide numerical evidence that this happens in practical situations, for some multi-dimensional distributions and that stochastic gradient descent exhibits similar behavior. We also provide empirical results on how the choice of initialization and optimizer can influence this behavior.","url_abs":"https://arxiv.org/abs/2002.04861v3","url_pdf":"https://arxiv.org/pdf/2002.04861v3.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-two-layer-relu-networks-with","repo_url":"https://github.com/dholzmueller/nn_inconsistency","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-two-layer-relu-networks-with","repo_url":"https://github.com/MindSpore-scientific/code-2/tree/main/Two-Layer-ReLU-Network-Analytically","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"training-two-layer-relu-networks-with","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/4/Two-Layer-ReLU-Network-Analytically","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[{"method_slug":"linear-regression","method_name":"Linear Regression"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2002.04861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.04861"}},"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/pwc-1/Paper-9/tree/main/4/Two-Layer-ReLU-Network-Analytically","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dholzmueller/nn_inconsistency","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-2/tree/main/Two-Layer-ReLU-Network-Analytically","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"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":"48a9e72de39ad385","entry":"expand","repo":"dholzmueller/nn_inconsistency","repo_kind":"official","path":"mc_training.py","file_url":"https://github.com/dholzmueller/nn_inconsistency/blob/HEAD/mc_training.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"48a9e72de39ad385"}},{"code_sha256_prefix":"e643e1fb516de6c9","entry":"get_statistics_dicts","repo":"dholzmueller/nn_inconsistency","repo_kind":"official","path":"mc_plotting.py","file_url":"https://github.com/dholzmueller/nn_inconsistency/blob/HEAD/mc_plotting.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e643e1fb516de6c9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}