{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DWLIKICFMCI4NBVPWOSGEXXLQJ","short_pith_number":"pith:DWLIKICF","schema_version":"1.0","canonical_sha256":"1d968520456091c686afb3a4625eeb827a9938b59b97a28fc551f3eedf930746","source":{"kind":"arxiv","id":"1801.02309","version":4},"attestation_state":"computed","paper":{"title":"Log-concave sampling: Metropolis-Hastings algorithms are fast","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"stat.ML","authors_text":"Bin Yu, Martin J. Wainwright, Raaz Dwivedi, Yuansi Chen","submitted_at":"2018-01-08T05:39:14Z","abstract_excerpt":"We consider the problem of sampling from a strongly log-concave density in $\\mathbb{R}^d$, and prove a non-asymptotic upper bound on the mixing time of the Metropolis-adjusted Langevin algorithm (MALA). The method draws samples by simulating a Markov chain obtained from the discretization of an appropriate Langevin diffusion, combined with an accept-reject step. Relative to known guarantees for the unadjusted Langevin algorithm (ULA), our bounds show that the use of an accept-reject step in MALA leads to an exponentially improved dependence on the error-tolerance. Concretely, in order to obtai"},"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":"1801.02309","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-08T05:39:14Z","cross_cats_sorted":["stat.CO"],"title_canon_sha256":"5be6d49a00b8a6538a549a665a4d8a28f4a3aed240b5994dabd3671533787712","abstract_canon_sha256":"96955735411667bcd4cbabf74f29a8f50df9f4ae1f6042bc3d4c4894b8b6525e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:25:23.595543Z","signature_b64":"ccJlu/39WWlOSIRoen5BIf+i1VgVIB1nMROi9PjKpvLuMScuFZ9FoQt/+H21eSEoPReXa36LqjTPZcuEKgHHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d968520456091c686afb3a4625eeb827a9938b59b97a28fc551f3eedf930746","last_reissued_at":"2026-07-05T00:25:23.594929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:25:23.594929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Log-concave sampling: Metropolis-Hastings algorithms are fast","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"stat.ML","authors_text":"Bin Yu, Martin J. Wainwright, Raaz Dwivedi, Yuansi Chen","submitted_at":"2018-01-08T05:39:14Z","abstract_excerpt":"We consider the problem of sampling from a strongly log-concave density in $\\mathbb{R}^d$, and prove a non-asymptotic upper bound on the mixing time of the Metropolis-adjusted Langevin algorithm (MALA). The method draws samples by simulating a Markov chain obtained from the discretization of an appropriate Langevin diffusion, combined with an accept-reject step. Relative to known guarantees for the unadjusted Langevin algorithm (ULA), our bounds show that the use of an accept-reject step in MALA leads to an exponentially improved dependence on the error-tolerance. Concretely, in order to obtai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.02309","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/1801.02309/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":"1801.02309","created_at":"2026-07-05T00:25:23.595042+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.02309v4","created_at":"2026-07-05T00:25:23.595042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.02309","created_at":"2026-07-05T00:25:23.595042+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWLIKICFMCI4","created_at":"2026-07-05T00:25:23.595042+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWLIKICFMCI4NBVP","created_at":"2026-07-05T00:25:23.595042+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWLIKICF","created_at":"2026-07-05T00:25:23.595042+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.10859","citing_title":"High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DWLIKICFMCI4NBVPWOSGEXXLQJ","json":"https://pith.science/pith/DWLIKICFMCI4NBVPWOSGEXXLQJ.json","graph_json":"https://pith.science/api/pith-number/DWLIKICFMCI4NBVPWOSGEXXLQJ/graph.json","events_json":"https://pith.science/api/pith-number/DWLIKICFMCI4NBVPWOSGEXXLQJ/events.json","paper":"https://pith.science/paper/DWLIKICF"},"agent_actions":{"view_html":"https://pith.science/pith/DWLIKICFMCI4NBVPWOSGEXXLQJ","download_json":"https://pith.science/pith/DWLIKICFMCI4NBVPWOSGEXXLQJ.json","view_paper":"https://pith.science/paper/DWLIKICF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.02309&json=true","fetch_graph":"https://pith.science/api/pith-number/DWLIKICFMCI4NBVPWOSGEXXLQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DWLIKICFMCI4NBVPWOSGEXXLQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWLIKICFMCI4NBVPWOSGEXXLQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWLIKICFMCI4NBVPWOSGEXXLQJ/action/storage_attestation","attest_author":"https://pith.science/pith/DWLIKICFMCI4NBVPWOSGEXXLQJ/action/author_attestation","sign_citation":"https://pith.science/pith/DWLIKICFMCI4NBVPWOSGEXXLQJ/action/citation_signature","submit_replication":"https://pith.science/pith/DWLIKICFMCI4NBVPWOSGEXXLQJ/action/replication_record"}},"created_at":"2026-07-05T00:25:23.595042+00:00","updated_at":"2026-07-05T00:25:23.595042+00:00"}