{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:XQSP23YPWTBFJMHEREQ43V43B5","short_pith_number":"pith:XQSP23YP","schema_version":"1.0","canonical_sha256":"bc24fd6f0fb4c254b0e48921cdd79b0f67c140f338589fe63d8caf9a9cdecdbe","source":{"kind":"arxiv","id":"1710.00095","version":4},"attestation_state":"computed","paper":{"title":"User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR","stat.CO","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Arnak S. Dalalyan, Avetik G. Karagulyan","submitted_at":"2017-09-29T21:15:03Z","abstract_excerpt":"In this paper, we study the problem of sampling from a given probability density function that is known to be smooth and strongly log-concave. We analyze several methods of approximate sampling based on discretizations of the (highly overdamped) Langevin diffusion and establish guarantees on its error measured in the Wasserstein-2 distance. Our guarantees improve or extend the state-of-the-art results in three directions. First, we provide an upper bound on the error of the first-order Langevin Monte Carlo (LMC) algorithm with optimized varying step-size. This result has the advantage of being"},"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":"1710.00095","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2017-09-29T21:15:03Z","cross_cats_sorted":["cs.LG","math.PR","stat.CO","stat.ML","stat.TH"],"title_canon_sha256":"a3aa1fd5dccd9c9545f0c2b0729cb1a040b1a8d30c6259b4d0a37e68218f4b6f","abstract_canon_sha256":"c14310b689e6087edf60569baa1c357f1e0c79858e85cc1bd3895ace298f9f6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:25.966997Z","signature_b64":"XXnAFytz/Gp2fWtf0U5mUBLs6BGzV47UGP5PfC92SG8zlP+A3U0aZSbkxjmkYVxlpJ1iR/OHhfrKaSqLDMCbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc24fd6f0fb4c254b0e48921cdd79b0f67c140f338589fe63d8caf9a9cdecdbe","last_reissued_at":"2026-07-05T07:48:25.966392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:25.966392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR","stat.CO","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Arnak S. Dalalyan, Avetik G. Karagulyan","submitted_at":"2017-09-29T21:15:03Z","abstract_excerpt":"In this paper, we study the problem of sampling from a given probability density function that is known to be smooth and strongly log-concave. We analyze several methods of approximate sampling based on discretizations of the (highly overdamped) Langevin diffusion and establish guarantees on its error measured in the Wasserstein-2 distance. Our guarantees improve or extend the state-of-the-art results in three directions. First, we provide an upper bound on the error of the first-order Langevin Monte Carlo (LMC) algorithm with optimized varying step-size. This result has the advantage of being"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.00095","kind":"arxiv","version":4},"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/1710.00095/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":"1710.00095","created_at":"2026-07-05T07:48:25.966469+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.00095v4","created_at":"2026-07-05T07:48:25.966469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.00095","created_at":"2026-07-05T07:48:25.966469+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQSP23YPWTBF","created_at":"2026-07-05T07:48:25.966469+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQSP23YPWTBFJMHE","created_at":"2026-07-05T07:48:25.966469+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQSP23YP","created_at":"2026-07-05T07:48:25.966469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.07637","citing_title":"Sampling from Boltzmann densities with physics informed low-rank formats","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XQSP23YPWTBFJMHEREQ43V43B5","json":"https://pith.science/pith/XQSP23YPWTBFJMHEREQ43V43B5.json","graph_json":"https://pith.science/api/pith-number/XQSP23YPWTBFJMHEREQ43V43B5/graph.json","events_json":"https://pith.science/api/pith-number/XQSP23YPWTBFJMHEREQ43V43B5/events.json","paper":"https://pith.science/paper/XQSP23YP"},"agent_actions":{"view_html":"https://pith.science/pith/XQSP23YPWTBFJMHEREQ43V43B5","download_json":"https://pith.science/pith/XQSP23YPWTBFJMHEREQ43V43B5.json","view_paper":"https://pith.science/paper/XQSP23YP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.00095&json=true","fetch_graph":"https://pith.science/api/pith-number/XQSP23YPWTBFJMHEREQ43V43B5/graph.json","fetch_events":"https://pith.science/api/pith-number/XQSP23YPWTBFJMHEREQ43V43B5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQSP23YPWTBFJMHEREQ43V43B5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQSP23YPWTBFJMHEREQ43V43B5/action/storage_attestation","attest_author":"https://pith.science/pith/XQSP23YPWTBFJMHEREQ43V43B5/action/author_attestation","sign_citation":"https://pith.science/pith/XQSP23YPWTBFJMHEREQ43V43B5/action/citation_signature","submit_replication":"https://pith.science/pith/XQSP23YPWTBFJMHEREQ43V43B5/action/replication_record"}},"created_at":"2026-07-05T07:48:25.966469+00:00","updated_at":"2026-07-05T07:48:25.966469+00:00"}