{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XN7CMN3L43NKS7XCDW7YPEEHSC","short_pith_number":"pith:XN7CMN3L","schema_version":"1.0","canonical_sha256":"bb7e26376be6daa97ee21dbf87908790882d8bfd85add7e29628c279c945cd0a","source":{"kind":"arxiv","id":"1807.01083","version":1},"attestation_state":"computed","paper":{"title":"A Mean-Field Optimal Control Formulation of Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Jiequn Han, Qianxiao Li, Weinan E","submitted_at":"2018-07-03T11:05:13Z","abstract_excerpt":"Recent work linking deep neural networks and dynamical systems opened up new avenues to analyze deep learning. In particular, it is observed that new insights can be obtained by recasting deep learning as an optimal control problem on difference or differential equations. However, the mathematical aspects of such a formulation have not been systematically explored. This paper introduces the mathematical formulation of the population risk minimization problem in deep learning as a mean-field optimal control problem. Mirroring the development of classical optimal control, we state and prove opti"},"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":"1807.01083","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-07-03T11:05:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0e3a7cda8bd79d8bd73ae975f9da0fc8469ce356b4faed79d7e737c47ace3116","abstract_canon_sha256":"c6f0ba594b05d9bc812ad4725632d799e15392a30f1cca0cea53740a5404c625"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:20:09.092035Z","signature_b64":"uVyMmP0bDBgupzH79xOt10hYQaP0ZU+o3GydrQDSwK62QcjPe2GEFDfd8n/V1zH0R8Kg3Zow7LyS0SxcD+n7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb7e26376be6daa97ee21dbf87908790882d8bfd85add7e29628c279c945cd0a","last_reissued_at":"2026-07-05T01:20:09.091555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:20:09.091555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Mean-Field Optimal Control Formulation of Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Jiequn Han, Qianxiao Li, Weinan E","submitted_at":"2018-07-03T11:05:13Z","abstract_excerpt":"Recent work linking deep neural networks and dynamical systems opened up new avenues to analyze deep learning. In particular, it is observed that new insights can be obtained by recasting deep learning as an optimal control problem on difference or differential equations. However, the mathematical aspects of such a formulation have not been systematically explored. This paper introduces the mathematical formulation of the population risk minimization problem in deep learning as a mean-field optimal control problem. Mirroring the development of classical optimal control, we state and prove opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01083","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/1807.01083/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":"1807.01083","created_at":"2026-07-05T01:20:09.091610+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.01083v1","created_at":"2026-07-05T01:20:09.091610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01083","created_at":"2026-07-05T01:20:09.091610+00:00"},{"alias_kind":"pith_short_12","alias_value":"XN7CMN3L43NK","created_at":"2026-07-05T01:20:09.091610+00:00"},{"alias_kind":"pith_short_16","alias_value":"XN7CMN3L43NKS7XC","created_at":"2026-07-05T01:20:09.091610+00:00"},{"alias_kind":"pith_short_8","alias_value":"XN7CMN3L","created_at":"2026-07-05T01:20:09.091610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07247","citing_title":"Theory of learning of high-dimensional controlled non-linear dynamical systems (I): models and methods","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"1907.06572","citing_title":"Deep network as memory space: complexity, generalization, disentangled representation and interpretability","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XN7CMN3L43NKS7XCDW7YPEEHSC","json":"https://pith.science/pith/XN7CMN3L43NKS7XCDW7YPEEHSC.json","graph_json":"https://pith.science/api/pith-number/XN7CMN3L43NKS7XCDW7YPEEHSC/graph.json","events_json":"https://pith.science/api/pith-number/XN7CMN3L43NKS7XCDW7YPEEHSC/events.json","paper":"https://pith.science/paper/XN7CMN3L"},"agent_actions":{"view_html":"https://pith.science/pith/XN7CMN3L43NKS7XCDW7YPEEHSC","download_json":"https://pith.science/pith/XN7CMN3L43NKS7XCDW7YPEEHSC.json","view_paper":"https://pith.science/paper/XN7CMN3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.01083&json=true","fetch_graph":"https://pith.science/api/pith-number/XN7CMN3L43NKS7XCDW7YPEEHSC/graph.json","fetch_events":"https://pith.science/api/pith-number/XN7CMN3L43NKS7XCDW7YPEEHSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XN7CMN3L43NKS7XCDW7YPEEHSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XN7CMN3L43NKS7XCDW7YPEEHSC/action/storage_attestation","attest_author":"https://pith.science/pith/XN7CMN3L43NKS7XCDW7YPEEHSC/action/author_attestation","sign_citation":"https://pith.science/pith/XN7CMN3L43NKS7XCDW7YPEEHSC/action/citation_signature","submit_replication":"https://pith.science/pith/XN7CMN3L43NKS7XCDW7YPEEHSC/action/replication_record"}},"created_at":"2026-07-05T01:20:09.091610+00:00","updated_at":"2026-07-05T01:20:09.091610+00:00"}