{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5I7HVEVVW6LT4SHMC7RVZF2354","short_pith_number":"pith:5I7HVEVV","schema_version":"1.0","canonical_sha256":"ea3e7a92b5b7973e48ec17e35c975bef0e76ac721db1459bb67c0140294651a1","source":{"kind":"arxiv","id":"2404.08792","version":1},"attestation_state":"computed","paper":{"title":"Convergence of coordinate ascent variational inference for log-concave measures via optimal transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","math.PR","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Daniel Lacker, Manuel Arnese","submitted_at":"2024-04-12T19:43:54Z","abstract_excerpt":"Mean field variational inference (VI) is the problem of finding the closest product (factorized) measure, in the sense of relative entropy, to a given high-dimensional probability measure $\\rho$. The well known Coordinate Ascent Variational Inference (CAVI) algorithm aims to approximate this product measure by iteratively optimizing over one coordinate (factor) at a time, which can be done explicitly. Despite its popularity, the convergence of CAVI remains poorly understood. In this paper, we prove the convergence of CAVI for log-concave densities $\\rho$. If additionally $\\log \\rho$ has Lipsch"},"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":"2404.08792","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-04-12T19:43:54Z","cross_cats_sorted":["cs.LG","math.OC","math.PR","math.ST","stat.TH"],"title_canon_sha256":"b8c383d5efad638d28245f884855c490f0f394df2cfa5e78b54f288758a78bb3","abstract_canon_sha256":"a5d6c268e6b10c9d1bf17f38097f72f4aea3c6ed81110604bfa6ba2ae8a15f33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:40.174660Z","signature_b64":"TDuywKD57G5yCNAO70VIw/zzRhYEm/KNZ45L4XMqrgY99SbqxRAcgJWu5uDePV7PvtWzBHzGTrLXwdf9wCeMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea3e7a92b5b7973e48ec17e35c975bef0e76ac721db1459bb67c0140294651a1","last_reissued_at":"2026-07-05T08:07:40.174181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:40.174181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of coordinate ascent variational inference for log-concave measures via optimal transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","math.PR","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Daniel Lacker, Manuel Arnese","submitted_at":"2024-04-12T19:43:54Z","abstract_excerpt":"Mean field variational inference (VI) is the problem of finding the closest product (factorized) measure, in the sense of relative entropy, to a given high-dimensional probability measure $\\rho$. The well known Coordinate Ascent Variational Inference (CAVI) algorithm aims to approximate this product measure by iteratively optimizing over one coordinate (factor) at a time, which can be done explicitly. Despite its popularity, the convergence of CAVI remains poorly understood. In this paper, we prove the convergence of CAVI for log-concave densities $\\rho$. If additionally $\\log \\rho$ has Lipsch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08792","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/2404.08792/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":"2404.08792","created_at":"2026-07-05T08:07:40.174236+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.08792v1","created_at":"2026-07-05T08:07:40.174236+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08792","created_at":"2026-07-05T08:07:40.174236+00:00"},{"alias_kind":"pith_short_12","alias_value":"5I7HVEVVW6LT","created_at":"2026-07-05T08:07:40.174236+00:00"},{"alias_kind":"pith_short_16","alias_value":"5I7HVEVVW6LT4SHM","created_at":"2026-07-05T08:07:40.174236+00:00"},{"alias_kind":"pith_short_8","alias_value":"5I7HVEVV","created_at":"2026-07-05T08:07:40.174236+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07006","citing_title":"Lectures on optimization","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5I7HVEVVW6LT4SHMC7RVZF2354","json":"https://pith.science/pith/5I7HVEVVW6LT4SHMC7RVZF2354.json","graph_json":"https://pith.science/api/pith-number/5I7HVEVVW6LT4SHMC7RVZF2354/graph.json","events_json":"https://pith.science/api/pith-number/5I7HVEVVW6LT4SHMC7RVZF2354/events.json","paper":"https://pith.science/paper/5I7HVEVV"},"agent_actions":{"view_html":"https://pith.science/pith/5I7HVEVVW6LT4SHMC7RVZF2354","download_json":"https://pith.science/pith/5I7HVEVVW6LT4SHMC7RVZF2354.json","view_paper":"https://pith.science/paper/5I7HVEVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.08792&json=true","fetch_graph":"https://pith.science/api/pith-number/5I7HVEVVW6LT4SHMC7RVZF2354/graph.json","fetch_events":"https://pith.science/api/pith-number/5I7HVEVVW6LT4SHMC7RVZF2354/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5I7HVEVVW6LT4SHMC7RVZF2354/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5I7HVEVVW6LT4SHMC7RVZF2354/action/storage_attestation","attest_author":"https://pith.science/pith/5I7HVEVVW6LT4SHMC7RVZF2354/action/author_attestation","sign_citation":"https://pith.science/pith/5I7HVEVVW6LT4SHMC7RVZF2354/action/citation_signature","submit_replication":"https://pith.science/pith/5I7HVEVVW6LT4SHMC7RVZF2354/action/replication_record"}},"created_at":"2026-07-05T08:07:40.174236+00:00","updated_at":"2026-07-05T08:07:40.174236+00:00"}