{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:E2WTNEP7A7IGDWCV4WLRLT3PQ2","short_pith_number":"pith:E2WTNEP7","schema_version":"1.0","canonical_sha256":"26ad3691ff07d061d855e59715cf6f86b72b30cdd27a8baacc6cd2e208621061","source":{"kind":"arxiv","id":"2202.01009","version":3},"attestation_state":"computed","paper":{"title":"Mean-Field Langevin Dynamics: Exponential Convergence and Annealing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"L\\'ena\\\"ic Chizat","submitted_at":"2022-02-02T13:07:09Z","abstract_excerpt":"Noisy particle gradient descent (NPGD) is an algorithm to minimize convex functions over the space of measures that include an entropy term. In the many-particle limit, this algorithm is described by a Mean-Field Langevin dynamics - a generalization of the Langevin dynamics with a non-linear drift - which is our main object of study. Previous work have shown its convergence to the unique minimizer via non-quantitative arguments. We prove that this dynamics converges at an exponential rate, under the assumption that a certain family of Log-Sobolev inequalities holds. This assumption holds for i"},"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":"2202.01009","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2022-02-02T13:07:09Z","cross_cats_sorted":[],"title_canon_sha256":"36015867eeb216947cc23cc4c2f74463108a2e0fb8c066b376f4d8ccaaa4d7a1","abstract_canon_sha256":"cb9718ec0060d5ae099f92a87f29f94c62af296f9c7f8b023b71fcacdab55df6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:47:40.317651Z","signature_b64":"zCyS8K7TqOfQR8rQURR7JtqT3JmSGhkUMnpeluFUvbK1MeL1rflsNxXa55gSeZ+tcr0GaudJA9etQI21MC2YBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26ad3691ff07d061d855e59715cf6f86b72b30cdd27a8baacc6cd2e208621061","last_reissued_at":"2026-07-05T04:47:40.317204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:47:40.317204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mean-Field Langevin Dynamics: Exponential Convergence and Annealing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"L\\'ena\\\"ic Chizat","submitted_at":"2022-02-02T13:07:09Z","abstract_excerpt":"Noisy particle gradient descent (NPGD) is an algorithm to minimize convex functions over the space of measures that include an entropy term. In the many-particle limit, this algorithm is described by a Mean-Field Langevin dynamics - a generalization of the Langevin dynamics with a non-linear drift - which is our main object of study. Previous work have shown its convergence to the unique minimizer via non-quantitative arguments. We prove that this dynamics converges at an exponential rate, under the assumption that a certain family of Log-Sobolev inequalities holds. This assumption holds for i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.01009","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/2202.01009/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":"2202.01009","created_at":"2026-07-05T04:47:40.317253+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.01009v3","created_at":"2026-07-05T04:47:40.317253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.01009","created_at":"2026-07-05T04:47:40.317253+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2WTNEP7A7IG","created_at":"2026-07-05T04:47:40.317253+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2WTNEP7A7IGDWCV","created_at":"2026-07-05T04:47:40.317253+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2WTNEP7","created_at":"2026-07-05T04:47:40.317253+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22622","citing_title":"A note on convergence of Wasserstein policy optimization","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20235","citing_title":"Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2WTNEP7A7IGDWCV4WLRLT3PQ2","json":"https://pith.science/pith/E2WTNEP7A7IGDWCV4WLRLT3PQ2.json","graph_json":"https://pith.science/api/pith-number/E2WTNEP7A7IGDWCV4WLRLT3PQ2/graph.json","events_json":"https://pith.science/api/pith-number/E2WTNEP7A7IGDWCV4WLRLT3PQ2/events.json","paper":"https://pith.science/paper/E2WTNEP7"},"agent_actions":{"view_html":"https://pith.science/pith/E2WTNEP7A7IGDWCV4WLRLT3PQ2","download_json":"https://pith.science/pith/E2WTNEP7A7IGDWCV4WLRLT3PQ2.json","view_paper":"https://pith.science/paper/E2WTNEP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.01009&json=true","fetch_graph":"https://pith.science/api/pith-number/E2WTNEP7A7IGDWCV4WLRLT3PQ2/graph.json","fetch_events":"https://pith.science/api/pith-number/E2WTNEP7A7IGDWCV4WLRLT3PQ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2WTNEP7A7IGDWCV4WLRLT3PQ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2WTNEP7A7IGDWCV4WLRLT3PQ2/action/storage_attestation","attest_author":"https://pith.science/pith/E2WTNEP7A7IGDWCV4WLRLT3PQ2/action/author_attestation","sign_citation":"https://pith.science/pith/E2WTNEP7A7IGDWCV4WLRLT3PQ2/action/citation_signature","submit_replication":"https://pith.science/pith/E2WTNEP7A7IGDWCV4WLRLT3PQ2/action/replication_record"}},"created_at":"2026-07-05T04:47:40.317253+00:00","updated_at":"2026-07-05T04:47:40.317253+00:00"}