{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QBERCUOQHON45ED5R7X7TZU4Z2","short_pith_number":"pith:QBERCUOQ","schema_version":"1.0","canonical_sha256":"80491151d03b9bce907d8feff9e69cceaa713dd91e3351f2f980c5ae942ad937","source":{"kind":"arxiv","id":"1802.08671","version":2},"attestation_state":"computed","paper":{"title":"Langevin Monte Carlo and JKO splitting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Espen Bernton","submitted_at":"2018-02-23T18:40:26Z","abstract_excerpt":"Algorithms based on discretizing Langevin diffusion are popular tools for sampling from high-dimensional distributions. We develop novel connections between such Monte Carlo algorithms, the theory of Wasserstein gradient flow, and the operator splitting approach to solving PDEs. In particular, we show that a proximal version of the Unadjusted Langevin Algorithm corresponds to a scheme that alternates between solving the gradient flows of two specific functionals on the space of probability measures. Using this perspective, we derive some new non-asymptotic results on the convergence properties"},"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":"1802.08671","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2018-02-23T18:40:26Z","cross_cats_sorted":[],"title_canon_sha256":"20a26c98f1f796a499b7e72ec11d20517d1d9146eb5d84ec616aff430755021d","abstract_canon_sha256":"99be20667e9f187fd17f6b7e0cafb48f139d3ff2e7b889194727af6515dca71f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:36.370010Z","signature_b64":"vZIJeMzEssMXT254ntgeVgrKGn+jdf/RF+wT5O3IStRaiQuOTHFBjNWzBtfxVAIa2iBdm83dkkQUe1wtDZZMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80491151d03b9bce907d8feff9e69cceaa713dd91e3351f2f980c5ae942ad937","last_reissued_at":"2026-05-17T23:46:36.369461Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:36.369461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Langevin Monte Carlo and JKO splitting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Espen Bernton","submitted_at":"2018-02-23T18:40:26Z","abstract_excerpt":"Algorithms based on discretizing Langevin diffusion are popular tools for sampling from high-dimensional distributions. We develop novel connections between such Monte Carlo algorithms, the theory of Wasserstein gradient flow, and the operator splitting approach to solving PDEs. In particular, we show that a proximal version of the Unadjusted Langevin Algorithm corresponds to a scheme that alternates between solving the gradient flows of two specific functionals on the space of probability measures. Using this perspective, we derive some new non-asymptotic results on the convergence properties"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08671","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":""},"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":"1802.08671","created_at":"2026-05-17T23:46:36.369551+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.08671v2","created_at":"2026-05-17T23:46:36.369551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08671","created_at":"2026-05-17T23:46:36.369551+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBERCUOQHON4","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBERCUOQHON45ED5","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBERCUOQ","created_at":"2026-05-18T12:32:46.962924+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/QBERCUOQHON45ED5R7X7TZU4Z2","json":"https://pith.science/pith/QBERCUOQHON45ED5R7X7TZU4Z2.json","graph_json":"https://pith.science/api/pith-number/QBERCUOQHON45ED5R7X7TZU4Z2/graph.json","events_json":"https://pith.science/api/pith-number/QBERCUOQHON45ED5R7X7TZU4Z2/events.json","paper":"https://pith.science/paper/QBERCUOQ"},"agent_actions":{"view_html":"https://pith.science/pith/QBERCUOQHON45ED5R7X7TZU4Z2","download_json":"https://pith.science/pith/QBERCUOQHON45ED5R7X7TZU4Z2.json","view_paper":"https://pith.science/paper/QBERCUOQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.08671&json=true","fetch_graph":"https://pith.science/api/pith-number/QBERCUOQHON45ED5R7X7TZU4Z2/graph.json","fetch_events":"https://pith.science/api/pith-number/QBERCUOQHON45ED5R7X7TZU4Z2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBERCUOQHON45ED5R7X7TZU4Z2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBERCUOQHON45ED5R7X7TZU4Z2/action/storage_attestation","attest_author":"https://pith.science/pith/QBERCUOQHON45ED5R7X7TZU4Z2/action/author_attestation","sign_citation":"https://pith.science/pith/QBERCUOQHON45ED5R7X7TZU4Z2/action/citation_signature","submit_replication":"https://pith.science/pith/QBERCUOQHON45ED5R7X7TZU4Z2/action/replication_record"}},"created_at":"2026-05-17T23:46:36.369551+00:00","updated_at":"2026-05-17T23:46:36.369551+00:00"}