{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X655UCT6HKRBBHDJWYTKM65ZU4","short_pith_number":"pith:X655UCT6","schema_version":"1.0","canonical_sha256":"bfbbda0a7e3aa2109c69b626a67bb9a73d8512db53497e9824b699463637b547","source":{"kind":"arxiv","id":"2407.16936","version":2},"attestation_state":"computed","paper":{"title":"Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.CO","stat.TH"],"primary_cat":"stat.ML","authors_text":"Molei Tao, Wei Guo, Yongxin Chen","submitted_at":"2024-07-24T02:15:48Z","abstract_excerpt":"We consider the outstanding problem of sampling from an unnormalized density that may be non-log-concave and multimodal. To enhance the performance of simple Markov chain Monte Carlo (MCMC) methods, techniques of annealing type have been widely used. However, quantitative theoretical guarantees of these techniques are under-explored. This study takes a first step toward providing a non-asymptotic analysis of annealed MCMC. Specifically, we establish, for the first time, an oracle complexity of $\\widetilde{O}\\left(\\frac{d\\beta^2{\\cal A}^2}{\\varepsilon^6}\\right)$ for the simple annealed Langevin"},"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":"2407.16936","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-07-24T02:15:48Z","cross_cats_sorted":["cs.LG","math.ST","stat.CO","stat.TH"],"title_canon_sha256":"178af6706ae3a4839c848d5ac5bd99ce489046c571717c014f6c159726bffb5f","abstract_canon_sha256":"b1a170232cbff41cafcc2df373d6a2a8affe441855ddfe2d388d8bdb7a4141fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:18.417186Z","signature_b64":"K0JnZ9Ly1rBdN7+9WEO3HUFZ0e4wy/S6lTmsiiAHZnqU4snpFae9It6ofQ65AtKASEWYg/q5lqqjsBrorhXrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfbbda0a7e3aa2109c69b626a67bb9a73d8512db53497e9824b699463637b547","last_reissued_at":"2026-07-05T10:15:18.416737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:18.416737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.CO","stat.TH"],"primary_cat":"stat.ML","authors_text":"Molei Tao, Wei Guo, Yongxin Chen","submitted_at":"2024-07-24T02:15:48Z","abstract_excerpt":"We consider the outstanding problem of sampling from an unnormalized density that may be non-log-concave and multimodal. To enhance the performance of simple Markov chain Monte Carlo (MCMC) methods, techniques of annealing type have been widely used. However, quantitative theoretical guarantees of these techniques are under-explored. This study takes a first step toward providing a non-asymptotic analysis of annealed MCMC. Specifically, we establish, for the first time, an oracle complexity of $\\widetilde{O}\\left(\\frac{d\\beta^2{\\cal A}^2}{\\varepsilon^6}\\right)$ for the simple annealed Langevin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16936","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/2407.16936/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":"2407.16936","created_at":"2026-07-05T10:15:18.416794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16936v2","created_at":"2026-07-05T10:15:18.416794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16936","created_at":"2026-07-05T10:15:18.416794+00:00"},{"alias_kind":"pith_short_12","alias_value":"X655UCT6HKRB","created_at":"2026-07-05T10:15:18.416794+00:00"},{"alias_kind":"pith_short_16","alias_value":"X655UCT6HKRBBHDJ","created_at":"2026-07-05T10:15:18.416794+00:00"},{"alias_kind":"pith_short_8","alias_value":"X655UCT6","created_at":"2026-07-05T10:15:18.416794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06538","citing_title":"Diffusion-Based Posterior Sampling: A Feynman-Kac Analysis of Bias and Stability","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X655UCT6HKRBBHDJWYTKM65ZU4","json":"https://pith.science/pith/X655UCT6HKRBBHDJWYTKM65ZU4.json","graph_json":"https://pith.science/api/pith-number/X655UCT6HKRBBHDJWYTKM65ZU4/graph.json","events_json":"https://pith.science/api/pith-number/X655UCT6HKRBBHDJWYTKM65ZU4/events.json","paper":"https://pith.science/paper/X655UCT6"},"agent_actions":{"view_html":"https://pith.science/pith/X655UCT6HKRBBHDJWYTKM65ZU4","download_json":"https://pith.science/pith/X655UCT6HKRBBHDJWYTKM65ZU4.json","view_paper":"https://pith.science/paper/X655UCT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16936&json=true","fetch_graph":"https://pith.science/api/pith-number/X655UCT6HKRBBHDJWYTKM65ZU4/graph.json","fetch_events":"https://pith.science/api/pith-number/X655UCT6HKRBBHDJWYTKM65ZU4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X655UCT6HKRBBHDJWYTKM65ZU4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X655UCT6HKRBBHDJWYTKM65ZU4/action/storage_attestation","attest_author":"https://pith.science/pith/X655UCT6HKRBBHDJWYTKM65ZU4/action/author_attestation","sign_citation":"https://pith.science/pith/X655UCT6HKRBBHDJWYTKM65ZU4/action/citation_signature","submit_replication":"https://pith.science/pith/X655UCT6HKRBBHDJWYTKM65ZU4/action/replication_record"}},"created_at":"2026-07-05T10:15:18.416794+00:00","updated_at":"2026-07-05T10:15:18.416794+00:00"}