{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZP2SIIQ4SJREY6RFLO5TF52RWX","short_pith_number":"pith:ZP2SIIQ4","schema_version":"1.0","canonical_sha256":"cbf524221c92624c7a255bbb32f751b5d6bb26fc12b02f38d186d26ffb7ed15c","source":{"kind":"arxiv","id":"2001.03040","version":8},"attestation_state":"computed","paper":{"title":"Deep Network Approximation for Smooth Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Haizhao Yang, Jianfeng Lu, Shijun Zhang, Zuowei Shen","submitted_at":"2020-01-09T15:06:10Z","abstract_excerpt":"This paper establishes the (nearly) optimal approximation error characterization of deep rectified linear unit (ReLU) networks for smooth functions in terms of both width and depth simultaneously. To that end, we first prove that multivariate polynomials can be approximated by deep ReLU networks of width $\\mathcal{O}(N)$ and depth $\\mathcal{O}(L)$ with an approximation error $\\mathcal{O}(N^{-L})$. Through local Taylor expansions and their deep ReLU network approximations, we show that deep ReLU networks of width $\\mathcal{O}(N\\ln N)$ and depth $\\mathcal{O}(L\\ln L)$ can approximate $f\\in C^s([0"},"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":"2001.03040","kind":"arxiv","version":8},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-09T15:06:10Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"cb0b088fc7dc0572a0c3b3fe8b103927c50e8b8dbb12dd55cb75c0868e7de344","abstract_canon_sha256":"ded6c00ab58348ef8d89a912ce3b7eb4495b2c1606c7b1a716d0461012013d16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:54.524125Z","signature_b64":"rL/hy6Zu0pBcw0cZJv2YLD4B/gBYq6ZmV8p0jwP9BYf+UxWgbGbUpUKgQXQkDFPE8lcTTg7sNt+J4mKPH1TYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbf524221c92624c7a255bbb32f751b5d6bb26fc12b02f38d186d26ffb7ed15c","last_reissued_at":"2026-07-05T03:27:54.523653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:54.523653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Network Approximation for Smooth Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Haizhao Yang, Jianfeng Lu, Shijun Zhang, Zuowei Shen","submitted_at":"2020-01-09T15:06:10Z","abstract_excerpt":"This paper establishes the (nearly) optimal approximation error characterization of deep rectified linear unit (ReLU) networks for smooth functions in terms of both width and depth simultaneously. To that end, we first prove that multivariate polynomials can be approximated by deep ReLU networks of width $\\mathcal{O}(N)$ and depth $\\mathcal{O}(L)$ with an approximation error $\\mathcal{O}(N^{-L})$. Through local Taylor expansions and their deep ReLU network approximations, we show that deep ReLU networks of width $\\mathcal{O}(N\\ln N)$ and depth $\\mathcal{O}(L\\ln L)$ can approximate $f\\in C^s([0"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.03040","kind":"arxiv","version":8},"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/2001.03040/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":"2001.03040","created_at":"2026-07-05T03:27:54.523710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.03040v8","created_at":"2026-07-05T03:27:54.523710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.03040","created_at":"2026-07-05T03:27:54.523710+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZP2SIIQ4SJRE","created_at":"2026-07-05T03:27:54.523710+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZP2SIIQ4SJREY6RF","created_at":"2026-07-05T03:27:54.523710+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZP2SIIQ4","created_at":"2026-07-05T03:27:54.523710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2112.14523","citing_title":"Deep neural network approximation theory for high-dimensional functions","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZP2SIIQ4SJREY6RFLO5TF52RWX","json":"https://pith.science/pith/ZP2SIIQ4SJREY6RFLO5TF52RWX.json","graph_json":"https://pith.science/api/pith-number/ZP2SIIQ4SJREY6RFLO5TF52RWX/graph.json","events_json":"https://pith.science/api/pith-number/ZP2SIIQ4SJREY6RFLO5TF52RWX/events.json","paper":"https://pith.science/paper/ZP2SIIQ4"},"agent_actions":{"view_html":"https://pith.science/pith/ZP2SIIQ4SJREY6RFLO5TF52RWX","download_json":"https://pith.science/pith/ZP2SIIQ4SJREY6RFLO5TF52RWX.json","view_paper":"https://pith.science/paper/ZP2SIIQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.03040&json=true","fetch_graph":"https://pith.science/api/pith-number/ZP2SIIQ4SJREY6RFLO5TF52RWX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZP2SIIQ4SJREY6RFLO5TF52RWX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZP2SIIQ4SJREY6RFLO5TF52RWX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZP2SIIQ4SJREY6RFLO5TF52RWX/action/storage_attestation","attest_author":"https://pith.science/pith/ZP2SIIQ4SJREY6RFLO5TF52RWX/action/author_attestation","sign_citation":"https://pith.science/pith/ZP2SIIQ4SJREY6RFLO5TF52RWX/action/citation_signature","submit_replication":"https://pith.science/pith/ZP2SIIQ4SJREY6RFLO5TF52RWX/action/replication_record"}},"created_at":"2026-07-05T03:27:54.523710+00:00","updated_at":"2026-07-05T03:27:54.523710+00:00"}