{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S2KQ3SAA5EQLK5E4RQESZAAWXA","short_pith_number":"pith:S2KQ3SAA","schema_version":"1.0","canonical_sha256":"96950dc800e920b5749c8c092c8016b80707f12975d3bd476411d22df597d54b","source":{"kind":"arxiv","id":"2405.18098","version":3},"attestation_state":"computed","paper":{"title":"Analysis of Primal-Dual Langevin Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Lorenz Kuger, Lukas Weigand, Martin Burger, Matthias J. Ehrhardt","submitted_at":"2024-05-28T12:02:56Z","abstract_excerpt":"We analyze a recently proposed class of algorithms for the problem of sampling from probability distributions $\\mu^\\ast$ in $\\mathbb{R}^d$ with a Lebesgue density of the form $\\mu^\\ast(x) \\propto \\exp(-f(Kx)-g(x))$, where $K$ is a linear operator and $f,g$ convex and non-smooth. The method is a generalization of the primal-dual hybrid gradient optimization algorithm to a sampling scheme. We give the iteration's continuous time limit, a stochastic differential equation in the joint primal-dual variable, and its mean field limit Fokker-Planck equation. Under mild conditions, the scheme converges"},"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":"2405.18098","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-05-28T12:02:56Z","cross_cats_sorted":[],"title_canon_sha256":"b64ce9a5252602009d39a2b002c9b59ad697fa683f5200b108504c9f3ce50311","abstract_canon_sha256":"ce3489c1f3e3a9cad3ba5d829767c90341bf5365f42fa06aad938f4789a86508"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:03.156425Z","signature_b64":"9/blYPDEcq6rKJH3Z1c5dYjaqexsbmQ+tvhETbmgvZX72pKDc3rWEl4dxJErMcZFSP2zZgnUkLUaHBwBkyC1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96950dc800e920b5749c8c092c8016b80707f12975d3bd476411d22df597d54b","last_reissued_at":"2026-07-05T09:31:03.155904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:03.155904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analysis of Primal-Dual Langevin Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Lorenz Kuger, Lukas Weigand, Martin Burger, Matthias J. Ehrhardt","submitted_at":"2024-05-28T12:02:56Z","abstract_excerpt":"We analyze a recently proposed class of algorithms for the problem of sampling from probability distributions $\\mu^\\ast$ in $\\mathbb{R}^d$ with a Lebesgue density of the form $\\mu^\\ast(x) \\propto \\exp(-f(Kx)-g(x))$, where $K$ is a linear operator and $f,g$ convex and non-smooth. The method is a generalization of the primal-dual hybrid gradient optimization algorithm to a sampling scheme. We give the iteration's continuous time limit, a stochastic differential equation in the joint primal-dual variable, and its mean field limit Fokker-Planck equation. Under mild conditions, the scheme converges"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18098","kind":"arxiv","version":3},"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/2405.18098/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":"2405.18098","created_at":"2026-07-05T09:31:03.155962+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18098v3","created_at":"2026-07-05T09:31:03.155962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18098","created_at":"2026-07-05T09:31:03.155962+00:00"},{"alias_kind":"pith_short_12","alias_value":"S2KQ3SAA5EQL","created_at":"2026-07-05T09:31:03.155962+00:00"},{"alias_kind":"pith_short_16","alias_value":"S2KQ3SAA5EQLK5E4","created_at":"2026-07-05T09:31:03.155962+00:00"},{"alias_kind":"pith_short_8","alias_value":"S2KQ3SAA","created_at":"2026-07-05T09:31:03.155962+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.12051","citing_title":"Ergodicity of Langevin Dynamics and its Discretizations for Non-smooth Potentials","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S2KQ3SAA5EQLK5E4RQESZAAWXA","json":"https://pith.science/pith/S2KQ3SAA5EQLK5E4RQESZAAWXA.json","graph_json":"https://pith.science/api/pith-number/S2KQ3SAA5EQLK5E4RQESZAAWXA/graph.json","events_json":"https://pith.science/api/pith-number/S2KQ3SAA5EQLK5E4RQESZAAWXA/events.json","paper":"https://pith.science/paper/S2KQ3SAA"},"agent_actions":{"view_html":"https://pith.science/pith/S2KQ3SAA5EQLK5E4RQESZAAWXA","download_json":"https://pith.science/pith/S2KQ3SAA5EQLK5E4RQESZAAWXA.json","view_paper":"https://pith.science/paper/S2KQ3SAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18098&json=true","fetch_graph":"https://pith.science/api/pith-number/S2KQ3SAA5EQLK5E4RQESZAAWXA/graph.json","fetch_events":"https://pith.science/api/pith-number/S2KQ3SAA5EQLK5E4RQESZAAWXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S2KQ3SAA5EQLK5E4RQESZAAWXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S2KQ3SAA5EQLK5E4RQESZAAWXA/action/storage_attestation","attest_author":"https://pith.science/pith/S2KQ3SAA5EQLK5E4RQESZAAWXA/action/author_attestation","sign_citation":"https://pith.science/pith/S2KQ3SAA5EQLK5E4RQESZAAWXA/action/citation_signature","submit_replication":"https://pith.science/pith/S2KQ3SAA5EQLK5E4RQESZAAWXA/action/replication_record"}},"created_at":"2026-07-05T09:31:03.155962+00:00","updated_at":"2026-07-05T09:31:03.155962+00:00"}