{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PHMUCXND6RJVOCFPG4DH3XPIT7","short_pith_number":"pith:PHMUCXND","schema_version":"1.0","canonical_sha256":"79d9415da3f4535708af37067ddde89ff380e821322b2428ac0ab160f8ec9dff","source":{"kind":"arxiv","id":"2401.07187","version":3},"attestation_state":"computed","paper":{"title":"A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Guang Cheng, Namjoon Suh","submitted_at":"2024-01-14T02:30:19Z","abstract_excerpt":"In this article, we review the literature on statistical theories of neural networks from three perspectives: approximation, training dynamics and generative models. In the first part, results on excess risks for neural networks are reviewed in the nonparametric framework of regression (and classification in Appendix~{\\color{blue}B}). These results rely on explicit constructions of neural networks, leading to fast convergence rates of excess risks. Nonetheless, their underlying analysis only applies to the global minimizer in the highly non-convex landscape of deep neural networks. This motiva"},"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":"2401.07187","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2024-01-14T02:30:19Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"f4f7b08b0dccaaab5318e9cffd0f5a3c0c098a5efec0072ae7cfadd11b9b7ac9","abstract_canon_sha256":"ed9820c1fb14ce0d28560c237ec831d81d6bcb9f7e3c4f888f8c0e51ecdde839"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:25.823600Z","signature_b64":"NQk3CYYcCbn+D9RY03srwEiwd+mzS4ZiCEftXMcnS0uWcszRdTF719KdBs3lDnrMSoE6fyT5M0mQBBAPeSd/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79d9415da3f4535708af37067ddde89ff380e821322b2428ac0ab160f8ec9dff","last_reissued_at":"2026-07-05T09:07:25.823153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:25.823153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Guang Cheng, Namjoon Suh","submitted_at":"2024-01-14T02:30:19Z","abstract_excerpt":"In this article, we review the literature on statistical theories of neural networks from three perspectives: approximation, training dynamics and generative models. In the first part, results on excess risks for neural networks are reviewed in the nonparametric framework of regression (and classification in Appendix~{\\color{blue}B}). These results rely on explicit constructions of neural networks, leading to fast convergence rates of excess risks. Nonetheless, their underlying analysis only applies to the global minimizer in the highly non-convex landscape of deep neural networks. This motiva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07187","kind":"arxiv","version":3},"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/2401.07187/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":"2401.07187","created_at":"2026-07-05T09:07:25.823205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.07187v3","created_at":"2026-07-05T09:07:25.823205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07187","created_at":"2026-07-05T09:07:25.823205+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHMUCXND6RJV","created_at":"2026-07-05T09:07:25.823205+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHMUCXND6RJVOCFP","created_at":"2026-07-05T09:07:25.823205+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHMUCXND","created_at":"2026-07-05T09:07:25.823205+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/PHMUCXND6RJVOCFPG4DH3XPIT7","json":"https://pith.science/pith/PHMUCXND6RJVOCFPG4DH3XPIT7.json","graph_json":"https://pith.science/api/pith-number/PHMUCXND6RJVOCFPG4DH3XPIT7/graph.json","events_json":"https://pith.science/api/pith-number/PHMUCXND6RJVOCFPG4DH3XPIT7/events.json","paper":"https://pith.science/paper/PHMUCXND"},"agent_actions":{"view_html":"https://pith.science/pith/PHMUCXND6RJVOCFPG4DH3XPIT7","download_json":"https://pith.science/pith/PHMUCXND6RJVOCFPG4DH3XPIT7.json","view_paper":"https://pith.science/paper/PHMUCXND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.07187&json=true","fetch_graph":"https://pith.science/api/pith-number/PHMUCXND6RJVOCFPG4DH3XPIT7/graph.json","fetch_events":"https://pith.science/api/pith-number/PHMUCXND6RJVOCFPG4DH3XPIT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHMUCXND6RJVOCFPG4DH3XPIT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHMUCXND6RJVOCFPG4DH3XPIT7/action/storage_attestation","attest_author":"https://pith.science/pith/PHMUCXND6RJVOCFPG4DH3XPIT7/action/author_attestation","sign_citation":"https://pith.science/pith/PHMUCXND6RJVOCFPG4DH3XPIT7/action/citation_signature","submit_replication":"https://pith.science/pith/PHMUCXND6RJVOCFPG4DH3XPIT7/action/replication_record"}},"created_at":"2026-07-05T09:07:25.823205+00:00","updated_at":"2026-07-05T09:07:25.823205+00:00"}