{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:754HICQRWHOE7SMHXS4TB5SMA3","short_pith_number":"pith:754HICQR","schema_version":"1.0","canonical_sha256":"ff78740a11b1dc4fc987bcb930f64c06ce58a048a5578fa85b6e0fe8bc8df192","source":{"kind":"arxiv","id":"1911.01469","version":1},"attestation_state":"computed","paper":{"title":"Proximal Langevin Algorithm: Rapid Convergence Under Isoperimetry","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Andre Wibisono","submitted_at":"2019-11-04T19:57:38Z","abstract_excerpt":"We study the Proximal Langevin Algorithm (PLA) for sampling from a probability distribution $\\nu = e^{-f}$ on $\\mathbb{R}^n$ under isoperimetry. We prove a convergence guarantee for PLA in Kullback-Leibler (KL) divergence when $\\nu$ satisfies log-Sobolev inequality (LSI) and $f$ has bounded second and third derivatives. This improves on the result for the Unadjusted Langevin Algorithm (ULA), and matches the fastest known rate for sampling under LSI (without Metropolis filter) with a better dependence on the LSI constant. We also prove convergence guarantees for PLA in R\\'enyi divergence of ord"},"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":"1911.01469","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-04T19:57:38Z","cross_cats_sorted":["cs.DS","cs.IT","cs.LG","math.IT"],"title_canon_sha256":"5aaba9ab7b52d467862c1ca069383c2ea03f2622337b38402a17b663f37353c4","abstract_canon_sha256":"81523abdd85c64fef1d85bebff11cec077040aafc8421beb68143acf61814d1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:51.087435Z","signature_b64":"kwd6uReED760cXmm2VLUzzvjDOHIBI35fRI3uy9DQgf0nN1ahZ92nWdPzAHNAdUVgFl9Fpifnqn3PUUDp7UODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff78740a11b1dc4fc987bcb930f64c06ce58a048a5578fa85b6e0fe8bc8df192","last_reissued_at":"2026-07-05T00:16:51.086978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:51.086978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Proximal Langevin Algorithm: Rapid Convergence Under Isoperimetry","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Andre Wibisono","submitted_at":"2019-11-04T19:57:38Z","abstract_excerpt":"We study the Proximal Langevin Algorithm (PLA) for sampling from a probability distribution $\\nu = e^{-f}$ on $\\mathbb{R}^n$ under isoperimetry. We prove a convergence guarantee for PLA in Kullback-Leibler (KL) divergence when $\\nu$ satisfies log-Sobolev inequality (LSI) and $f$ has bounded second and third derivatives. This improves on the result for the Unadjusted Langevin Algorithm (ULA), and matches the fastest known rate for sampling under LSI (without Metropolis filter) with a better dependence on the LSI constant. We also prove convergence guarantees for PLA in R\\'enyi divergence of ord"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.01469","kind":"arxiv","version":1},"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/1911.01469/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":"1911.01469","created_at":"2026-07-05T00:16:51.087041+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.01469v1","created_at":"2026-07-05T00:16:51.087041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.01469","created_at":"2026-07-05T00:16:51.087041+00:00"},{"alias_kind":"pith_short_12","alias_value":"754HICQRWHOE","created_at":"2026-07-05T00:16:51.087041+00:00"},{"alias_kind":"pith_short_16","alias_value":"754HICQRWHOE7SMH","created_at":"2026-07-05T00:16:51.087041+00:00"},{"alias_kind":"pith_short_8","alias_value":"754HICQR","created_at":"2026-07-05T00:16:51.087041+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.07999","citing_title":"Fast Mixing of Data Augmentation Algorithms: Bayesian Probit, Logit, and Lasso Regression","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12461","citing_title":"A proximal gradient algorithm for composite log-concave sampling","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/754HICQRWHOE7SMHXS4TB5SMA3","json":"https://pith.science/pith/754HICQRWHOE7SMHXS4TB5SMA3.json","graph_json":"https://pith.science/api/pith-number/754HICQRWHOE7SMHXS4TB5SMA3/graph.json","events_json":"https://pith.science/api/pith-number/754HICQRWHOE7SMHXS4TB5SMA3/events.json","paper":"https://pith.science/paper/754HICQR"},"agent_actions":{"view_html":"https://pith.science/pith/754HICQRWHOE7SMHXS4TB5SMA3","download_json":"https://pith.science/pith/754HICQRWHOE7SMHXS4TB5SMA3.json","view_paper":"https://pith.science/paper/754HICQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.01469&json=true","fetch_graph":"https://pith.science/api/pith-number/754HICQRWHOE7SMHXS4TB5SMA3/graph.json","fetch_events":"https://pith.science/api/pith-number/754HICQRWHOE7SMHXS4TB5SMA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/754HICQRWHOE7SMHXS4TB5SMA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/754HICQRWHOE7SMHXS4TB5SMA3/action/storage_attestation","attest_author":"https://pith.science/pith/754HICQRWHOE7SMHXS4TB5SMA3/action/author_attestation","sign_citation":"https://pith.science/pith/754HICQRWHOE7SMHXS4TB5SMA3/action/citation_signature","submit_replication":"https://pith.science/pith/754HICQRWHOE7SMHXS4TB5SMA3/action/replication_record"}},"created_at":"2026-07-05T00:16:51.087041+00:00","updated_at":"2026-07-05T00:16:51.087041+00:00"}