{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:TPHJXAQZOYXHKPQYXF4PA2AWPG","short_pith_number":"pith:TPHJXAQZ","schema_version":"1.0","canonical_sha256":"9bce9b8219762e753e18b978f0681679a5814e49f16bb62439cdb9ffb583422f","source":{"kind":"arxiv","id":"1503.08060","version":2},"attestation_state":"computed","paper":{"title":"Expectation Propagation in the large-data limit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"stat.CO","authors_text":"Guillaume Dehaene, Simon Barthelm\\'e","submitted_at":"2015-03-27T13:15:42Z","abstract_excerpt":"Expectation Propagation (Minka, 2001) is a widely successful algorithm for variational inference. EP is an iterative algorithm used to approximate complicated distributions, typically to find a Gaussian approximation of posterior distributions. In many applications of this type, EP performs extremely well. Surprisingly, despite its widespread use, there are very few theoretical guarantees on Gaussian EP, and it is quite poorly understood.\n  In order to analyze EP, we first introduce a variant of EP: averaged-EP (aEP), which operates on a smaller parameter space. We then consider aEP and EP in "},"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":"1503.08060","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2015-03-27T13:15:42Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"7749ce6f2e122a866bc18b09faa53edcc627a9dc84c3be5cec650d6b6e2b206f","abstract_canon_sha256":"ad67bcc403c99675cd3713a1ed82831b55a9c3c37e9c8691822919cc3c511dcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:18:00.098615Z","signature_b64":"as5sUgZiITaKlm1lecMroRD2/v43Vma4eooZ5fLAjavMD4ASgHwGSQr+S/d2qgyDKjVjobLTRiHKALEi/a42DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bce9b8219762e753e18b978f0681679a5814e49f16bb62439cdb9ffb583422f","last_reissued_at":"2026-05-18T01:18:00.097828Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:18:00.097828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expectation Propagation in the large-data limit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"stat.CO","authors_text":"Guillaume Dehaene, Simon Barthelm\\'e","submitted_at":"2015-03-27T13:15:42Z","abstract_excerpt":"Expectation Propagation (Minka, 2001) is a widely successful algorithm for variational inference. EP is an iterative algorithm used to approximate complicated distributions, typically to find a Gaussian approximation of posterior distributions. In many applications of this type, EP performs extremely well. Surprisingly, despite its widespread use, there are very few theoretical guarantees on Gaussian EP, and it is quite poorly understood.\n  In order to analyze EP, we first introduce a variant of EP: averaged-EP (aEP), which operates on a smaller parameter space. We then consider aEP and EP in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.08060","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":""},"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":"1503.08060","created_at":"2026-05-18T01:18:00.097951+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.08060v2","created_at":"2026-05-18T01:18:00.097951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.08060","created_at":"2026-05-18T01:18:00.097951+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPHJXAQZOYXH","created_at":"2026-05-18T12:29:42.218222+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPHJXAQZOYXHKPQY","created_at":"2026-05-18T12:29:42.218222+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPHJXAQZ","created_at":"2026-05-18T12:29:42.218222+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/TPHJXAQZOYXHKPQYXF4PA2AWPG","json":"https://pith.science/pith/TPHJXAQZOYXHKPQYXF4PA2AWPG.json","graph_json":"https://pith.science/api/pith-number/TPHJXAQZOYXHKPQYXF4PA2AWPG/graph.json","events_json":"https://pith.science/api/pith-number/TPHJXAQZOYXHKPQYXF4PA2AWPG/events.json","paper":"https://pith.science/paper/TPHJXAQZ"},"agent_actions":{"view_html":"https://pith.science/pith/TPHJXAQZOYXHKPQYXF4PA2AWPG","download_json":"https://pith.science/pith/TPHJXAQZOYXHKPQYXF4PA2AWPG.json","view_paper":"https://pith.science/paper/TPHJXAQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.08060&json=true","fetch_graph":"https://pith.science/api/pith-number/TPHJXAQZOYXHKPQYXF4PA2AWPG/graph.json","fetch_events":"https://pith.science/api/pith-number/TPHJXAQZOYXHKPQYXF4PA2AWPG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPHJXAQZOYXHKPQYXF4PA2AWPG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPHJXAQZOYXHKPQYXF4PA2AWPG/action/storage_attestation","attest_author":"https://pith.science/pith/TPHJXAQZOYXHKPQYXF4PA2AWPG/action/author_attestation","sign_citation":"https://pith.science/pith/TPHJXAQZOYXHKPQYXF4PA2AWPG/action/citation_signature","submit_replication":"https://pith.science/pith/TPHJXAQZOYXHKPQYXF4PA2AWPG/action/replication_record"}},"created_at":"2026-05-18T01:18:00.097951+00:00","updated_at":"2026-05-18T01:18:00.097951+00:00"}