{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FWQMRZ65A5S4UU4LS4HYGGUJXQ","short_pith_number":"pith:FWQMRZ65","schema_version":"1.0","canonical_sha256":"2da0c8e7dd0765ca538b970f831a89bc20ba1bde719b68481018d14a5854f902","source":{"kind":"arxiv","id":"2312.16360","version":5},"attestation_state":"computed","paper":{"title":"Mean-field underdamped Langevin dynamics and its spacetime discretization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"stat.CO","authors_text":"Ashia Wilson, Qiang Fu","submitted_at":"2023-12-26T23:59:04Z","abstract_excerpt":"We propose a new method called the N-particle underdamped Langevin algorithm for optimizing a special class of non-linear functionals defined over the space of probability measures. Examples of problems with this formulation include training mean-field neural networks, maximum mean discrepancy minimization and kernel Stein discrepancy minimization. Our algorithm is based on a novel spacetime discretization of the mean-field underdamped Langevin dynamics, for which we provide a new, fast mixing guarantee. In addition, we demonstrate that our algorithm converges globally in total variation dista"},"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":"2312.16360","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.CO","submitted_at":"2023-12-26T23:59:04Z","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"f4bb0fe25038537281e3e6292f29be56873995b37cfcc0abba8d3761b780e8ab","abstract_canon_sha256":"e7b45714adc87b42baba585ef3135f957a627dcec1d69186258b446f1bf305b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:46.441297Z","signature_b64":"0NMxSsa1gBsSON1Papnm8CqEkbgkqGxzR8WYqt0Cxxpzy8xeN0lY6bsHjiCI8qGVkg4Qw+rYDCk3D7hxI4ZyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2da0c8e7dd0765ca538b970f831a89bc20ba1bde719b68481018d14a5854f902","last_reissued_at":"2026-07-05T07:41:46.440849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:46.440849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mean-field underdamped Langevin dynamics and its spacetime discretization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"stat.CO","authors_text":"Ashia Wilson, Qiang Fu","submitted_at":"2023-12-26T23:59:04Z","abstract_excerpt":"We propose a new method called the N-particle underdamped Langevin algorithm for optimizing a special class of non-linear functionals defined over the space of probability measures. Examples of problems with this formulation include training mean-field neural networks, maximum mean discrepancy minimization and kernel Stein discrepancy minimization. Our algorithm is based on a novel spacetime discretization of the mean-field underdamped Langevin dynamics, for which we provide a new, fast mixing guarantee. In addition, we demonstrate that our algorithm converges globally in total variation dista"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16360","kind":"arxiv","version":5},"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/2312.16360/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":"2312.16360","created_at":"2026-07-05T07:41:46.440907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16360v5","created_at":"2026-07-05T07:41:46.440907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16360","created_at":"2026-07-05T07:41:46.440907+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWQMRZ65A5S4","created_at":"2026-07-05T07:41:46.440907+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWQMRZ65A5S4UU4L","created_at":"2026-07-05T07:41:46.440907+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWQMRZ65","created_at":"2026-07-05T07:41:46.440907+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02518","citing_title":"Exponential Ergodicity in Relative Entropy and $L^2$-Wasserstein Distance for non-equilibrium partially dissipative Kinetic SDEs","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FWQMRZ65A5S4UU4LS4HYGGUJXQ","json":"https://pith.science/pith/FWQMRZ65A5S4UU4LS4HYGGUJXQ.json","graph_json":"https://pith.science/api/pith-number/FWQMRZ65A5S4UU4LS4HYGGUJXQ/graph.json","events_json":"https://pith.science/api/pith-number/FWQMRZ65A5S4UU4LS4HYGGUJXQ/events.json","paper":"https://pith.science/paper/FWQMRZ65"},"agent_actions":{"view_html":"https://pith.science/pith/FWQMRZ65A5S4UU4LS4HYGGUJXQ","download_json":"https://pith.science/pith/FWQMRZ65A5S4UU4LS4HYGGUJXQ.json","view_paper":"https://pith.science/paper/FWQMRZ65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16360&json=true","fetch_graph":"https://pith.science/api/pith-number/FWQMRZ65A5S4UU4LS4HYGGUJXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/FWQMRZ65A5S4UU4LS4HYGGUJXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWQMRZ65A5S4UU4LS4HYGGUJXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWQMRZ65A5S4UU4LS4HYGGUJXQ/action/storage_attestation","attest_author":"https://pith.science/pith/FWQMRZ65A5S4UU4LS4HYGGUJXQ/action/author_attestation","sign_citation":"https://pith.science/pith/FWQMRZ65A5S4UU4LS4HYGGUJXQ/action/citation_signature","submit_replication":"https://pith.science/pith/FWQMRZ65A5S4UU4LS4HYGGUJXQ/action/replication_record"}},"created_at":"2026-07-05T07:41:46.440907+00:00","updated_at":"2026-07-05T07:41:46.440907+00:00"}