{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HQ56M4277GUG3HMCP4PZ766OPQ","short_pith_number":"pith:HQ56M427","schema_version":"1.0","canonical_sha256":"3c3be6735ff9a86d9d827f1f9ffbce7c0eea187494ea9f2f0d06b699b410706d","source":{"kind":"arxiv","id":"2207.05705","version":2},"attestation_state":"computed","paper":{"title":"Conservative SPDEs as fluctuating mean field limits of stochastic gradient descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.AP","stat.ML"],"primary_cat":"math.PR","authors_text":"Benjamin Gess, Rishabh S. Gvalani, Vitalii Konarovskyi","submitted_at":"2022-07-12T17:27:18Z","abstract_excerpt":"The convergence of stochastic interacting particle systems in the mean-field limit to solutions of conservative stochastic partial differential equations is established, with optimal rate of convergence. As a second main result, a quantitative central limit theorem for such SPDEs is derived, again, with optimal rate of convergence.\n  The results apply, in particular, to the convergence in the mean-field scaling of stochastic gradient descent dynamics in overparametrized, shallow neural networks to solutions of SPDEs. It is shown that the inclusion of fluctuations in the limiting SPDE improves "},"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":"2207.05705","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.PR","submitted_at":"2022-07-12T17:27:18Z","cross_cats_sorted":["cs.LG","math.AP","stat.ML"],"title_canon_sha256":"e7a8be7352b41dd946071ff7cf0457c64e59c88beec4e50b7f805c9e1da44c5c","abstract_canon_sha256":"dc13222509749d1be740ec6a5d09d5c3d9ab2c26783398289475839199b2e510"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:15.872944Z","signature_b64":"a1aiL5sNELTNYnBBaeJ7V3rgG/APqEHugXlOPl5JSCcUW49AGaEleUpKHZvjg723W7hrzHvB9sNPTVEVS42zDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c3be6735ff9a86d9d827f1f9ffbce7c0eea187494ea9f2f0d06b699b410706d","last_reissued_at":"2026-07-05T05:25:15.872503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:15.872503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conservative SPDEs as fluctuating mean field limits of stochastic gradient descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.AP","stat.ML"],"primary_cat":"math.PR","authors_text":"Benjamin Gess, Rishabh S. Gvalani, Vitalii Konarovskyi","submitted_at":"2022-07-12T17:27:18Z","abstract_excerpt":"The convergence of stochastic interacting particle systems in the mean-field limit to solutions of conservative stochastic partial differential equations is established, with optimal rate of convergence. As a second main result, a quantitative central limit theorem for such SPDEs is derived, again, with optimal rate of convergence.\n  The results apply, in particular, to the convergence in the mean-field scaling of stochastic gradient descent dynamics in overparametrized, shallow neural networks to solutions of SPDEs. It is shown that the inclusion of fluctuations in the limiting SPDE improves "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05705","kind":"arxiv","version":2},"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/2207.05705/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":"2207.05705","created_at":"2026-07-05T05:25:15.872560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.05705v2","created_at":"2026-07-05T05:25:15.872560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05705","created_at":"2026-07-05T05:25:15.872560+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQ56M4277GUG","created_at":"2026-07-05T05:25:15.872560+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQ56M4277GUG3HMC","created_at":"2026-07-05T05:25:15.872560+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQ56M427","created_at":"2026-07-05T05:25:15.872560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13655","citing_title":"Linearization of ergodic McKean SDEs and applications","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HQ56M4277GUG3HMCP4PZ766OPQ","json":"https://pith.science/pith/HQ56M4277GUG3HMCP4PZ766OPQ.json","graph_json":"https://pith.science/api/pith-number/HQ56M4277GUG3HMCP4PZ766OPQ/graph.json","events_json":"https://pith.science/api/pith-number/HQ56M4277GUG3HMCP4PZ766OPQ/events.json","paper":"https://pith.science/paper/HQ56M427"},"agent_actions":{"view_html":"https://pith.science/pith/HQ56M4277GUG3HMCP4PZ766OPQ","download_json":"https://pith.science/pith/HQ56M4277GUG3HMCP4PZ766OPQ.json","view_paper":"https://pith.science/paper/HQ56M427","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.05705&json=true","fetch_graph":"https://pith.science/api/pith-number/HQ56M4277GUG3HMCP4PZ766OPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/HQ56M4277GUG3HMCP4PZ766OPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQ56M4277GUG3HMCP4PZ766OPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQ56M4277GUG3HMCP4PZ766OPQ/action/storage_attestation","attest_author":"https://pith.science/pith/HQ56M4277GUG3HMCP4PZ766OPQ/action/author_attestation","sign_citation":"https://pith.science/pith/HQ56M4277GUG3HMCP4PZ766OPQ/action/citation_signature","submit_replication":"https://pith.science/pith/HQ56M4277GUG3HMCP4PZ766OPQ/action/replication_record"}},"created_at":"2026-07-05T05:25:15.872560+00:00","updated_at":"2026-07-05T05:25:15.872560+00:00"}