{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FTOIW2WEXM2XETWJQZALUXAA6Y","short_pith_number":"pith:FTOIW2WE","schema_version":"1.0","canonical_sha256":"2cdc8b6ac4bb35724ec98640ba5c00f63cc8e58edba30ad72491328d28ca0a0e","source":{"kind":"arxiv","id":"2405.15767","version":3},"attestation_state":"computed","paper":{"title":"Improved Particle Approximation Error for Mean Field Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Atsushi Nitanda","submitted_at":"2024-05-24T17:59:06Z","abstract_excerpt":"Mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex functional defined over the space of probability distributions. MFLD has gained attention due to its connection with noisy gradient descent for mean-field two-layer neural networks. Unlike standard Langevin dynamics, the nonlinearity of the objective functional induces particle interactions, necessitating multiple particles to approximate the dynamics in a finite-particle setting. Recent works (Chen et al., 2022; Suzuki et al., 2023b) have demonstrated the uniform-in-time propagation of chaos for MFLD, showin"},"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":"2405.15767","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T17:59:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d5592597154d585e5133a4901e46acf29d0954728d4f295e08c6cbe00600242a","abstract_canon_sha256":"49a64440f9d7ca62d9d415eee6a53b2d4d2d5862cad5c39d03a91175659f0e35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:31.212906Z","signature_b64":"W82NQR5Tdb6ESCwqKXL00O0RxViHJWvnUqSL45rqL4n3O1ITxvRWoxf0C0g3xIkKm70aWd6vKaAj9xSD2ZOSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cdc8b6ac4bb35724ec98640ba5c00f63cc8e58edba30ad72491328d28ca0a0e","last_reissued_at":"2026-07-05T09:28:31.212485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:31.212485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Particle Approximation Error for Mean Field Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Atsushi Nitanda","submitted_at":"2024-05-24T17:59:06Z","abstract_excerpt":"Mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex functional defined over the space of probability distributions. MFLD has gained attention due to its connection with noisy gradient descent for mean-field two-layer neural networks. Unlike standard Langevin dynamics, the nonlinearity of the objective functional induces particle interactions, necessitating multiple particles to approximate the dynamics in a finite-particle setting. Recent works (Chen et al., 2022; Suzuki et al., 2023b) have demonstrated the uniform-in-time propagation of chaos for MFLD, showin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15767","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/2405.15767/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":"2405.15767","created_at":"2026-07-05T09:28:31.212543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15767v3","created_at":"2026-07-05T09:28:31.212543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15767","created_at":"2026-07-05T09:28:31.212543+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTOIW2WEXM2X","created_at":"2026-07-05T09:28:31.212543+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTOIW2WEXM2XETWJ","created_at":"2026-07-05T09:28:31.212543+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTOIW2WE","created_at":"2026-07-05T09:28:31.212543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12385","citing_title":"Convergence of drift-diffusion PDEs arising as Wasserstein gradient flows of convex functions","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FTOIW2WEXM2XETWJQZALUXAA6Y","json":"https://pith.science/pith/FTOIW2WEXM2XETWJQZALUXAA6Y.json","graph_json":"https://pith.science/api/pith-number/FTOIW2WEXM2XETWJQZALUXAA6Y/graph.json","events_json":"https://pith.science/api/pith-number/FTOIW2WEXM2XETWJQZALUXAA6Y/events.json","paper":"https://pith.science/paper/FTOIW2WE"},"agent_actions":{"view_html":"https://pith.science/pith/FTOIW2WEXM2XETWJQZALUXAA6Y","download_json":"https://pith.science/pith/FTOIW2WEXM2XETWJQZALUXAA6Y.json","view_paper":"https://pith.science/paper/FTOIW2WE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15767&json=true","fetch_graph":"https://pith.science/api/pith-number/FTOIW2WEXM2XETWJQZALUXAA6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/FTOIW2WEXM2XETWJQZALUXAA6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTOIW2WEXM2XETWJQZALUXAA6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTOIW2WEXM2XETWJQZALUXAA6Y/action/storage_attestation","attest_author":"https://pith.science/pith/FTOIW2WEXM2XETWJQZALUXAA6Y/action/author_attestation","sign_citation":"https://pith.science/pith/FTOIW2WEXM2XETWJQZALUXAA6Y/action/citation_signature","submit_replication":"https://pith.science/pith/FTOIW2WEXM2XETWJQZALUXAA6Y/action/replication_record"}},"created_at":"2026-07-05T09:28:31.212543+00:00","updated_at":"2026-07-05T09:28:31.212543+00:00"}