{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WQV34ZHXLDZEIN73VIER4VXI5J","short_pith_number":"pith:WQV34ZHX","schema_version":"1.0","canonical_sha256":"b42bbe64f758f24437fbaa091e56e8ea7f812ad17461a339f22487edff8417a4","source":{"kind":"arxiv","id":"2101.03446","version":2},"attestation_state":"computed","paper":{"title":"The shifted ODE method for underdamped Langevin MCMC","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.PR","math.ST","stat.TH"],"primary_cat":"math.NA","authors_text":"Harald Oberhauser, James Foster, Terry Lyons","submitted_at":"2021-01-10T00:05:01Z","abstract_excerpt":"In this paper, we consider the underdamped Langevin diffusion (ULD) and propose a numerical approximation using its associated ordinary differential equation (ODE). When used as a Markov Chain Monte Carlo (MCMC) algorithm, we show that the ODE approximation achieves a $2$-Wasserstein error of $\\varepsilon$ in $\\mathcal{O}\\big(d^{\\frac{1}{3}}/\\varepsilon^{\\frac{2}{3}}\\big)$ steps under the standard smoothness and strong convexity assumptions on the target distribution. This matches the complexity of the randomized midpoint method proposed by Shen and Lee [NeurIPS 2019] which was shown to be ord"},"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":"2101.03446","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2021-01-10T00:05:01Z","cross_cats_sorted":["cs.NA","math.PR","math.ST","stat.TH"],"title_canon_sha256":"1bcc67b3a1eb10f1dfe4354886586ba0c67cf032a071784ebfb6b5970de84991","abstract_canon_sha256":"9dc31b83fc2e936597987e950f6779478a135fb29388610c72a71474ab81e2b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:09:16.065409Z","signature_b64":"jedKPdRAp4T+ytoDXxd4SACuOBenBI17ok0TbSomosR+6aeakqDoOvNEy8Boi61KJGrJ4l3FM3qvH6uVPGJKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b42bbe64f758f24437fbaa091e56e8ea7f812ad17461a339f22487edff8417a4","last_reissued_at":"2026-07-05T02:09:16.064984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:09:16.064984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The shifted ODE method for underdamped Langevin MCMC","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.PR","math.ST","stat.TH"],"primary_cat":"math.NA","authors_text":"Harald Oberhauser, James Foster, Terry Lyons","submitted_at":"2021-01-10T00:05:01Z","abstract_excerpt":"In this paper, we consider the underdamped Langevin diffusion (ULD) and propose a numerical approximation using its associated ordinary differential equation (ODE). When used as a Markov Chain Monte Carlo (MCMC) algorithm, we show that the ODE approximation achieves a $2$-Wasserstein error of $\\varepsilon$ in $\\mathcal{O}\\big(d^{\\frac{1}{3}}/\\varepsilon^{\\frac{2}{3}}\\big)$ steps under the standard smoothness and strong convexity assumptions on the target distribution. This matches the complexity of the randomized midpoint method proposed by Shen and Lee [NeurIPS 2019] which was shown to be ord"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.03446","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/2101.03446/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":"2101.03446","created_at":"2026-07-05T02:09:16.065038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.03446v2","created_at":"2026-07-05T02:09:16.065038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.03446","created_at":"2026-07-05T02:09:16.065038+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQV34ZHXLDZE","created_at":"2026-07-05T02:09:16.065038+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQV34ZHXLDZEIN73","created_at":"2026-07-05T02:09:16.065038+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQV34ZHX","created_at":"2026-07-05T02:09:16.065038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.03949","citing_title":"Analysis of kinetic Langevin Monte Carlo under the stochastic exponential Euler discretization from underdamped all the way to overdamped","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQV34ZHXLDZEIN73VIER4VXI5J","json":"https://pith.science/pith/WQV34ZHXLDZEIN73VIER4VXI5J.json","graph_json":"https://pith.science/api/pith-number/WQV34ZHXLDZEIN73VIER4VXI5J/graph.json","events_json":"https://pith.science/api/pith-number/WQV34ZHXLDZEIN73VIER4VXI5J/events.json","paper":"https://pith.science/paper/WQV34ZHX"},"agent_actions":{"view_html":"https://pith.science/pith/WQV34ZHXLDZEIN73VIER4VXI5J","download_json":"https://pith.science/pith/WQV34ZHXLDZEIN73VIER4VXI5J.json","view_paper":"https://pith.science/paper/WQV34ZHX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.03446&json=true","fetch_graph":"https://pith.science/api/pith-number/WQV34ZHXLDZEIN73VIER4VXI5J/graph.json","fetch_events":"https://pith.science/api/pith-number/WQV34ZHXLDZEIN73VIER4VXI5J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQV34ZHXLDZEIN73VIER4VXI5J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQV34ZHXLDZEIN73VIER4VXI5J/action/storage_attestation","attest_author":"https://pith.science/pith/WQV34ZHXLDZEIN73VIER4VXI5J/action/author_attestation","sign_citation":"https://pith.science/pith/WQV34ZHXLDZEIN73VIER4VXI5J/action/citation_signature","submit_replication":"https://pith.science/pith/WQV34ZHXLDZEIN73VIER4VXI5J/action/replication_record"}},"created_at":"2026-07-05T02:09:16.065038+00:00","updated_at":"2026-07-05T02:09:16.065038+00:00"}