{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OLE73HN7JM2CPA4KBKSWEWYKV6","short_pith_number":"pith:OLE73HN7","schema_version":"1.0","canonical_sha256":"72c9fd9dbf4b3427838a0aa5625b0aaf8a18ce91bf05a57a6301dfb6299763e3","source":{"kind":"arxiv","id":"1912.03921","version":1},"attestation_state":"computed","paper":{"title":"On the rate of convergence of a neural network regression estimate learned by gradient descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Alina Braun, Harro Walk, Michael Kohler","submitted_at":"2019-12-09T09:36:35Z","abstract_excerpt":"Nonparametric regression with random design is considered. Estimates are defined by minimzing a penalized empirical $L_2$ risk over a suitably chosen class of neural networks with one hidden layer via gradient descent. Here, the gradient descent procedure is repeated several times with randomly chosen starting values for the weights, and from the list of constructed estimates the one with the minimal empirical $L_2$ risk is chosen. Under the assumption that the number of randomly chosen starting values and the number of steps for gradient descent are sufficiently large it is shown that the res"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1912.03921","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-12-09T09:36:35Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"822aa31494263415696e594555fba7495522aa8cfd5aac0b53587a4cafa9138d","abstract_canon_sha256":"94d1ba6da89c282a454e425e899bfdba3a1e6936454c904086e28e1588ca0028"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:50.088976Z","signature_b64":"xodvnvFsv0fYLO1tTCjnX594Et9EstFK6StrcvqsDfb0gyRNILX3x5x18fiGNv9xlVaztSEm5plXKD/FdQWzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72c9fd9dbf4b3427838a0aa5625b0aaf8a18ce91bf05a57a6301dfb6299763e3","last_reissued_at":"2026-07-05T00:24:50.088621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:50.088621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the rate of convergence of a neural network regression estimate learned by gradient descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Alina Braun, Harro Walk, Michael Kohler","submitted_at":"2019-12-09T09:36:35Z","abstract_excerpt":"Nonparametric regression with random design is considered. Estimates are defined by minimzing a penalized empirical $L_2$ risk over a suitably chosen class of neural networks with one hidden layer via gradient descent. Here, the gradient descent procedure is repeated several times with randomly chosen starting values for the weights, and from the list of constructed estimates the one with the minimal empirical $L_2$ risk is chosen. Under the assumption that the number of randomly chosen starting values and the number of steps for gradient descent are sufficiently large it is shown that the res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03921","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.03921/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1912.03921","created_at":"2026-07-05T00:24:50.088683+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.03921v1","created_at":"2026-07-05T00:24:50.088683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03921","created_at":"2026-07-05T00:24:50.088683+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLE73HN7JM2C","created_at":"2026-07-05T00:24:50.088683+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLE73HN7JM2CPA4K","created_at":"2026-07-05T00:24:50.088683+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLE73HN7","created_at":"2026-07-05T00:24:50.088683+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OLE73HN7JM2CPA4KBKSWEWYKV6","json":"https://pith.science/pith/OLE73HN7JM2CPA4KBKSWEWYKV6.json","graph_json":"https://pith.science/api/pith-number/OLE73HN7JM2CPA4KBKSWEWYKV6/graph.json","events_json":"https://pith.science/api/pith-number/OLE73HN7JM2CPA4KBKSWEWYKV6/events.json","paper":"https://pith.science/paper/OLE73HN7"},"agent_actions":{"view_html":"https://pith.science/pith/OLE73HN7JM2CPA4KBKSWEWYKV6","download_json":"https://pith.science/pith/OLE73HN7JM2CPA4KBKSWEWYKV6.json","view_paper":"https://pith.science/paper/OLE73HN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.03921&json=true","fetch_graph":"https://pith.science/api/pith-number/OLE73HN7JM2CPA4KBKSWEWYKV6/graph.json","fetch_events":"https://pith.science/api/pith-number/OLE73HN7JM2CPA4KBKSWEWYKV6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLE73HN7JM2CPA4KBKSWEWYKV6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLE73HN7JM2CPA4KBKSWEWYKV6/action/storage_attestation","attest_author":"https://pith.science/pith/OLE73HN7JM2CPA4KBKSWEWYKV6/action/author_attestation","sign_citation":"https://pith.science/pith/OLE73HN7JM2CPA4KBKSWEWYKV6/action/citation_signature","submit_replication":"https://pith.science/pith/OLE73HN7JM2CPA4KBKSWEWYKV6/action/replication_record"}},"created_at":"2026-07-05T00:24:50.088683+00:00","updated_at":"2026-07-05T00:24:50.088683+00:00"}