{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4NXNG3HUSKALGGIJ5WA2HJ6QSS","short_pith_number":"pith:4NXNG3HU","schema_version":"1.0","canonical_sha256":"e36ed36cf49280b31909ed81a3a7d094b77bec522f2285efbb146be9ab825d2d","source":{"kind":"arxiv","id":"2405.05679","version":2},"attestation_state":"computed","paper":{"title":"Non-asymptotic estimates for accelerated high order Langevin Monte Carlo algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","stat.CO","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Ariel Neufeld, Ying Zhang","submitted_at":"2024-05-09T11:12:03Z","abstract_excerpt":"In this paper, we propose two new algorithms, namely, aHOLA and aHOLLA, to sample from high-dimensional target distributions with possibly super-linearly growing potentials. We establish non-asymptotic convergence bounds for aHOLA in Wasserstein-1 and Wasserstein-2 distances with rates of convergence equal to $1+q/2$ and $1/2+q/4$, respectively, under a local H\\\"{o}lder condition with exponent $q\\in(0,1]$ and a convexity at infinity condition on the potential of the target distribution. Similar results are obtained for aHOLLA under certain global continuity conditions and a dissipativity condi"},"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":"2405.05679","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2024-05-09T11:12:03Z","cross_cats_sorted":["math.PR","stat.CO","stat.ML","stat.TH"],"title_canon_sha256":"a19377146a4e227aab351a01d6213226a60b0d9f191437837d92afb8c2bd47ce","abstract_canon_sha256":"0dfcc08323fb87bffdcb91120a5a29450fd901b737d48f5931e5ccc2273b6dd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:26.912535Z","signature_b64":"DD3EYPd6s7qBzqSpv4FTYXI1+Z/5CkdlkXu8tBMEumyst+GTG0Hf1DM3fSc0HdK6j4UKRlPb+9EPjV5jWgkSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e36ed36cf49280b31909ed81a3a7d094b77bec522f2285efbb146be9ab825d2d","last_reissued_at":"2026-07-05T11:50:26.912026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:26.912026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-asymptotic estimates for accelerated high order Langevin Monte Carlo algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","stat.CO","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Ariel Neufeld, Ying Zhang","submitted_at":"2024-05-09T11:12:03Z","abstract_excerpt":"In this paper, we propose two new algorithms, namely, aHOLA and aHOLLA, to sample from high-dimensional target distributions with possibly super-linearly growing potentials. We establish non-asymptotic convergence bounds for aHOLA in Wasserstein-1 and Wasserstein-2 distances with rates of convergence equal to $1+q/2$ and $1/2+q/4$, respectively, under a local H\\\"{o}lder condition with exponent $q\\in(0,1]$ and a convexity at infinity condition on the potential of the target distribution. Similar results are obtained for aHOLLA under certain global continuity conditions and a dissipativity condi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05679","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/2405.05679/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":"2405.05679","created_at":"2026-07-05T11:50:26.912086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.05679v2","created_at":"2026-07-05T11:50:26.912086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05679","created_at":"2026-07-05T11:50:26.912086+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NXNG3HUSKAL","created_at":"2026-07-05T11:50:26.912086+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NXNG3HUSKALGGIJ","created_at":"2026-07-05T11:50:26.912086+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NXNG3HU","created_at":"2026-07-05T11:50:26.912086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07939","citing_title":"Accelerating Langevin Monte Carlo via Efficient Stochastic Runge--Kutta Methods beyond Log-Concavity","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4NXNG3HUSKALGGIJ5WA2HJ6QSS","json":"https://pith.science/pith/4NXNG3HUSKALGGIJ5WA2HJ6QSS.json","graph_json":"https://pith.science/api/pith-number/4NXNG3HUSKALGGIJ5WA2HJ6QSS/graph.json","events_json":"https://pith.science/api/pith-number/4NXNG3HUSKALGGIJ5WA2HJ6QSS/events.json","paper":"https://pith.science/paper/4NXNG3HU"},"agent_actions":{"view_html":"https://pith.science/pith/4NXNG3HUSKALGGIJ5WA2HJ6QSS","download_json":"https://pith.science/pith/4NXNG3HUSKALGGIJ5WA2HJ6QSS.json","view_paper":"https://pith.science/paper/4NXNG3HU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.05679&json=true","fetch_graph":"https://pith.science/api/pith-number/4NXNG3HUSKALGGIJ5WA2HJ6QSS/graph.json","fetch_events":"https://pith.science/api/pith-number/4NXNG3HUSKALGGIJ5WA2HJ6QSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NXNG3HUSKALGGIJ5WA2HJ6QSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NXNG3HUSKALGGIJ5WA2HJ6QSS/action/storage_attestation","attest_author":"https://pith.science/pith/4NXNG3HUSKALGGIJ5WA2HJ6QSS/action/author_attestation","sign_citation":"https://pith.science/pith/4NXNG3HUSKALGGIJ5WA2HJ6QSS/action/citation_signature","submit_replication":"https://pith.science/pith/4NXNG3HUSKALGGIJ5WA2HJ6QSS/action/replication_record"}},"created_at":"2026-07-05T11:50:26.912086+00:00","updated_at":"2026-07-05T11:50:26.912086+00:00"}