{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CYIHVGF5P3QG5S32PFU6W3Y3CJ","short_pith_number":"pith:CYIHVGF5","schema_version":"1.0","canonical_sha256":"16107a98bd7ee06ecb7a7969eb6f1b127dbc2266a9baf2d49235cde9037b2883","source":{"kind":"arxiv","id":"2112.12662","version":2},"attestation_state":"computed","paper":{"title":"Analysis of Langevin Monte Carlo from Poincar\\'e to Log-Sobolev","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Matthew Zhang, Mufan Bill Li, Murat A. Erdogdu, Ruoqi Shen, Sinho Chewi","submitted_at":"2021-12-23T15:56:33Z","abstract_excerpt":"Classically, the continuous-time Langevin diffusion converges exponentially fast to its stationary distribution $\\pi$ under the sole assumption that $\\pi$ satisfies a Poincar\\'e inequality. Using this fact to provide guarantees for the discrete-time Langevin Monte Carlo (LMC) algorithm, however, is considerably more challenging due to the need for working with chi-squared or R\\'enyi divergences, and prior works have largely focused on strongly log-concave targets. In this work, we provide the first convergence guarantees for LMC assuming that $\\pi$ satisfies either a Lata\\l{}a--Oleszkiewicz or"},"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":"2112.12662","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2021-12-23T15:56:33Z","cross_cats_sorted":["stat.ML","stat.TH"],"title_canon_sha256":"e127143518a051ce6cedecc000166f1bbb97a0790c8c922d784b927a4f9c195d","abstract_canon_sha256":"f2c43359800b7e6a9d5da003cedbd76be19b622467336e6d2474bdc696d081ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:20.200410Z","signature_b64":"UHoDLyG0elC+u28lTatcSqcz6um64RbEgbls7rwzaL1dGvQugkrgZ69xBiAIBx2T4MHu75+5AxYIo51WtFK9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16107a98bd7ee06ecb7a7969eb6f1b127dbc2266a9baf2d49235cde9037b2883","last_reissued_at":"2026-07-05T08:42:20.199987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:20.199987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analysis of Langevin Monte Carlo from Poincar\\'e to Log-Sobolev","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Matthew Zhang, Mufan Bill Li, Murat A. Erdogdu, Ruoqi Shen, Sinho Chewi","submitted_at":"2021-12-23T15:56:33Z","abstract_excerpt":"Classically, the continuous-time Langevin diffusion converges exponentially fast to its stationary distribution $\\pi$ under the sole assumption that $\\pi$ satisfies a Poincar\\'e inequality. Using this fact to provide guarantees for the discrete-time Langevin Monte Carlo (LMC) algorithm, however, is considerably more challenging due to the need for working with chi-squared or R\\'enyi divergences, and prior works have largely focused on strongly log-concave targets. In this work, we provide the first convergence guarantees for LMC assuming that $\\pi$ satisfies either a Lata\\l{}a--Oleszkiewicz or"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.12662","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/2112.12662/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":"2112.12662","created_at":"2026-07-05T08:42:20.200040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.12662v2","created_at":"2026-07-05T08:42:20.200040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.12662","created_at":"2026-07-05T08:42:20.200040+00:00"},{"alias_kind":"pith_short_12","alias_value":"CYIHVGF5P3QG","created_at":"2026-07-05T08:42:20.200040+00:00"},{"alias_kind":"pith_short_16","alias_value":"CYIHVGF5P3QG5S32","created_at":"2026-07-05T08:42:20.200040+00:00"},{"alias_kind":"pith_short_8","alias_value":"CYIHVGF5","created_at":"2026-07-05T08:42:20.200040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11170","citing_title":"Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data","ref_index":138,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CYIHVGF5P3QG5S32PFU6W3Y3CJ","json":"https://pith.science/pith/CYIHVGF5P3QG5S32PFU6W3Y3CJ.json","graph_json":"https://pith.science/api/pith-number/CYIHVGF5P3QG5S32PFU6W3Y3CJ/graph.json","events_json":"https://pith.science/api/pith-number/CYIHVGF5P3QG5S32PFU6W3Y3CJ/events.json","paper":"https://pith.science/paper/CYIHVGF5"},"agent_actions":{"view_html":"https://pith.science/pith/CYIHVGF5P3QG5S32PFU6W3Y3CJ","download_json":"https://pith.science/pith/CYIHVGF5P3QG5S32PFU6W3Y3CJ.json","view_paper":"https://pith.science/paper/CYIHVGF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.12662&json=true","fetch_graph":"https://pith.science/api/pith-number/CYIHVGF5P3QG5S32PFU6W3Y3CJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CYIHVGF5P3QG5S32PFU6W3Y3CJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CYIHVGF5P3QG5S32PFU6W3Y3CJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CYIHVGF5P3QG5S32PFU6W3Y3CJ/action/storage_attestation","attest_author":"https://pith.science/pith/CYIHVGF5P3QG5S32PFU6W3Y3CJ/action/author_attestation","sign_citation":"https://pith.science/pith/CYIHVGF5P3QG5S32PFU6W3Y3CJ/action/citation_signature","submit_replication":"https://pith.science/pith/CYIHVGF5P3QG5S32PFU6W3Y3CJ/action/replication_record"}},"created_at":"2026-07-05T08:42:20.200040+00:00","updated_at":"2026-07-05T08:42:20.200040+00:00"}