{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SD475ZUJL6YVMVOV3XCOGRL4N3","short_pith_number":"pith:SD475ZUJ","schema_version":"1.0","canonical_sha256":"90f9fee6895fb15655d5ddc4e3457c6ecb4be93a921d316f47c331636d2e34b7","source":{"kind":"arxiv","id":"1908.10859","version":2},"attestation_state":"computed","paper":{"title":"High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG","math.OC","stat.CO"],"primary_cat":"stat.ML","authors_text":"Martin J. Wainwright, Michael I. Jordan, Peter L. Bartlett, Wenlong Mou, Yi-An Ma","submitted_at":"2019-08-28T17:59:29Z","abstract_excerpt":"We propose a Markov chain Monte Carlo (MCMC) algorithm based on third-order Langevin dynamics for sampling from distributions with log-concave and smooth densities. The higher-order dynamics allow for more flexible discretization schemes, and we develop a specific method that combines splitting with more accurate integration. For a broad class of $d$-dimensional distributions arising from generalized linear models, we prove that the resulting third-order algorithm produces samples from a distribution that is at most $\\varepsilon > 0$ in Wasserstein distance from the target distribution in $O\\l"},"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":"1908.10859","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-28T17:59:29Z","cross_cats_sorted":["cs.DS","cs.LG","math.OC","stat.CO"],"title_canon_sha256":"56917828a18a67f1f91ad4e0320f886db4d4eafe5274c7e3e9c4d2453eb9e548","abstract_canon_sha256":"6db505added65d56d7390f606901decfb99480033398401fd9388ec6595c421a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:36.210102Z","signature_b64":"mi2BCwNNeJQ/35xN4Rh2PZErNcABRJfVNXVPPiPohiz7zHu96nYmTIt/SWL/JdXKI5Be9uicwZ2mlUu7yVzGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90f9fee6895fb15655d5ddc4e3457c6ecb4be93a921d316f47c331636d2e34b7","last_reissued_at":"2026-07-05T01:05:36.209681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:36.209681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG","math.OC","stat.CO"],"primary_cat":"stat.ML","authors_text":"Martin J. Wainwright, Michael I. Jordan, Peter L. Bartlett, Wenlong Mou, Yi-An Ma","submitted_at":"2019-08-28T17:59:29Z","abstract_excerpt":"We propose a Markov chain Monte Carlo (MCMC) algorithm based on third-order Langevin dynamics for sampling from distributions with log-concave and smooth densities. The higher-order dynamics allow for more flexible discretization schemes, and we develop a specific method that combines splitting with more accurate integration. For a broad class of $d$-dimensional distributions arising from generalized linear models, we prove that the resulting third-order algorithm produces samples from a distribution that is at most $\\varepsilon > 0$ in Wasserstein distance from the target distribution in $O\\l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10859","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/1908.10859/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":"1908.10859","created_at":"2026-07-05T01:05:36.209740+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.10859v2","created_at":"2026-07-05T01:05:36.209740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10859","created_at":"2026-07-05T01:05:36.209740+00:00"},{"alias_kind":"pith_short_12","alias_value":"SD475ZUJL6YV","created_at":"2026-07-05T01:05:36.209740+00:00"},{"alias_kind":"pith_short_16","alias_value":"SD475ZUJL6YVMVOV","created_at":"2026-07-05T01:05:36.209740+00:00"},{"alias_kind":"pith_short_8","alias_value":"SD475ZUJ","created_at":"2026-07-05T01:05:36.209740+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SD475ZUJL6YVMVOV3XCOGRL4N3","json":"https://pith.science/pith/SD475ZUJL6YVMVOV3XCOGRL4N3.json","graph_json":"https://pith.science/api/pith-number/SD475ZUJL6YVMVOV3XCOGRL4N3/graph.json","events_json":"https://pith.science/api/pith-number/SD475ZUJL6YVMVOV3XCOGRL4N3/events.json","paper":"https://pith.science/paper/SD475ZUJ"},"agent_actions":{"view_html":"https://pith.science/pith/SD475ZUJL6YVMVOV3XCOGRL4N3","download_json":"https://pith.science/pith/SD475ZUJL6YVMVOV3XCOGRL4N3.json","view_paper":"https://pith.science/paper/SD475ZUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.10859&json=true","fetch_graph":"https://pith.science/api/pith-number/SD475ZUJL6YVMVOV3XCOGRL4N3/graph.json","fetch_events":"https://pith.science/api/pith-number/SD475ZUJL6YVMVOV3XCOGRL4N3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SD475ZUJL6YVMVOV3XCOGRL4N3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SD475ZUJL6YVMVOV3XCOGRL4N3/action/storage_attestation","attest_author":"https://pith.science/pith/SD475ZUJL6YVMVOV3XCOGRL4N3/action/author_attestation","sign_citation":"https://pith.science/pith/SD475ZUJL6YVMVOV3XCOGRL4N3/action/citation_signature","submit_replication":"https://pith.science/pith/SD475ZUJL6YVMVOV3XCOGRL4N3/action/replication_record"}},"created_at":"2026-07-05T01:05:36.209740+00:00","updated_at":"2026-07-05T01:05:36.209740+00:00"}