{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MG7IWS3GOW3JUAIXTHTHM3M4CI","short_pith_number":"pith:MG7IWS3G","schema_version":"1.0","canonical_sha256":"61be8b4b6675b69a011799e6766d9c120c721999e98b1d970c4261be2922f0e6","source":{"kind":"arxiv","id":"2505.16145","version":1},"attestation_state":"computed","paper":{"title":"Exponential Convergence of CAVI for Bayesian PCA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Arghya Datta, Florian Maire, Philippe Gagnon","submitted_at":"2025-05-22T02:44:00Z","abstract_excerpt":"Probabilistic principal component analysis (PCA) and its Bayesian variant (BPCA) are widely used for dimension reduction in machine learning and statistics. The main advantage of probabilistic PCA over the traditional formulation is allowing uncertainty quantification. The parameters of BPCA are typically learned using mean-field variational inference, and in particular, the coordinate ascent variational inference (CAVI) algorithm. So far, the convergence speed of CAVI for BPCA has not been characterized. In our paper, we fill this gap in the literature. Firstly, we prove a precise exponential"},"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":"2505.16145","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-22T02:44:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"add085b04e8f57a05f58e5b9badf52308aea20a05d160b3295b3a2cb5932e3b2","abstract_canon_sha256":"9ea7fe2a7a520e88e508621d93be05d9267fae8428cc2b3941e55fc0c4b6e015"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:30.636767Z","signature_b64":"VAHC5kqmnRNAsdQZpF5vp4idwnBjlj7CidfGL97cDrx+WZtYpKse/m1jvlvF8Bv+2vzdHBtrU4L5+yjyWD9oCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61be8b4b6675b69a011799e6766d9c120c721999e98b1d970c4261be2922f0e6","last_reissued_at":"2026-07-05T11:07:30.636255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:30.636255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exponential Convergence of CAVI for Bayesian PCA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Arghya Datta, Florian Maire, Philippe Gagnon","submitted_at":"2025-05-22T02:44:00Z","abstract_excerpt":"Probabilistic principal component analysis (PCA) and its Bayesian variant (BPCA) are widely used for dimension reduction in machine learning and statistics. The main advantage of probabilistic PCA over the traditional formulation is allowing uncertainty quantification. The parameters of BPCA are typically learned using mean-field variational inference, and in particular, the coordinate ascent variational inference (CAVI) algorithm. So far, the convergence speed of CAVI for BPCA has not been characterized. In our paper, we fill this gap in the literature. Firstly, we prove a precise exponential"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16145","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/2505.16145/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":"2505.16145","created_at":"2026-07-05T11:07:30.636322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16145v1","created_at":"2026-07-05T11:07:30.636322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16145","created_at":"2026-07-05T11:07:30.636322+00:00"},{"alias_kind":"pith_short_12","alias_value":"MG7IWS3GOW3J","created_at":"2026-07-05T11:07:30.636322+00:00"},{"alias_kind":"pith_short_16","alias_value":"MG7IWS3GOW3JUAIX","created_at":"2026-07-05T11:07:30.636322+00:00"},{"alias_kind":"pith_short_8","alias_value":"MG7IWS3G","created_at":"2026-07-05T11:07:30.636322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MG7IWS3GOW3JUAIXTHTHM3M4CI","json":"https://pith.science/pith/MG7IWS3GOW3JUAIXTHTHM3M4CI.json","graph_json":"https://pith.science/api/pith-number/MG7IWS3GOW3JUAIXTHTHM3M4CI/graph.json","events_json":"https://pith.science/api/pith-number/MG7IWS3GOW3JUAIXTHTHM3M4CI/events.json","paper":"https://pith.science/paper/MG7IWS3G"},"agent_actions":{"view_html":"https://pith.science/pith/MG7IWS3GOW3JUAIXTHTHM3M4CI","download_json":"https://pith.science/pith/MG7IWS3GOW3JUAIXTHTHM3M4CI.json","view_paper":"https://pith.science/paper/MG7IWS3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16145&json=true","fetch_graph":"https://pith.science/api/pith-number/MG7IWS3GOW3JUAIXTHTHM3M4CI/graph.json","fetch_events":"https://pith.science/api/pith-number/MG7IWS3GOW3JUAIXTHTHM3M4CI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MG7IWS3GOW3JUAIXTHTHM3M4CI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MG7IWS3GOW3JUAIXTHTHM3M4CI/action/storage_attestation","attest_author":"https://pith.science/pith/MG7IWS3GOW3JUAIXTHTHM3M4CI/action/author_attestation","sign_citation":"https://pith.science/pith/MG7IWS3GOW3JUAIXTHTHM3M4CI/action/citation_signature","submit_replication":"https://pith.science/pith/MG7IWS3GOW3JUAIXTHTHM3M4CI/action/replication_record"}},"created_at":"2026-07-05T11:07:30.636322+00:00","updated_at":"2026-07-05T11:07:30.636322+00:00"}