{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:QHMN5FGY43FBRWHC6RSCLU24RR","short_pith_number":"pith:QHMN5FGY","schema_version":"1.0","canonical_sha256":"81d8de94d8e6ca18d8e2f46425d35c8c74a788ed03ad9480ae0fa61668fb1ef9","source":{"kind":"arxiv","id":"1512.09327","version":4},"attestation_state":"computed","paper":{"title":"Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Balaji Lakshminarayanan, Charles Blundell, Leonard Hasenclever, Sebastian Vollmer, Stefan Webb, Thibaut Lienart, Yee Whye Teh","submitted_at":"2015-12-31T17:30:45Z","abstract_excerpt":"This paper makes two contributions to Bayesian machine learning algorithms. Firstly, we propose stochastic natural gradient expectation propagation (SNEP), a novel alternative to expectation propagation (EP), a popular variational inference algorithm. SNEP is a black box variational algorithm, in that it does not require any simplifying assumptions on the distribution of interest, beyond the existence of some Monte Carlo sampler for estimating the moments of the EP tilted distributions. Further, as opposed to EP which has no guarantee of convergence, SNEP can be shown to be convergent, even wh"},"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":"1512.09327","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-31T17:30:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fe7ffd371393b947372da2bbe53f7c83bc026ab3c2743b696f51378e27d04ec5","abstract_canon_sha256":"289683485eeec6a9d2505b8521e1ec2b4f491051a13be1281e632590a22da59b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:49.036065Z","signature_b64":"J1olVUGrUWbhkE2VWN+To2p94aKLybfz6/7kNshry0bD5Rx2Vyh8mOkZpGfDl67pr8i9xHWNsoT6QrqOzkZsDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81d8de94d8e6ca18d8e2f46425d35c8c74a788ed03ad9480ae0fa61668fb1ef9","last_reissued_at":"2026-05-18T00:35:49.035463Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:49.035463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Balaji Lakshminarayanan, Charles Blundell, Leonard Hasenclever, Sebastian Vollmer, Stefan Webb, Thibaut Lienart, Yee Whye Teh","submitted_at":"2015-12-31T17:30:45Z","abstract_excerpt":"This paper makes two contributions to Bayesian machine learning algorithms. Firstly, we propose stochastic natural gradient expectation propagation (SNEP), a novel alternative to expectation propagation (EP), a popular variational inference algorithm. SNEP is a black box variational algorithm, in that it does not require any simplifying assumptions on the distribution of interest, beyond the existence of some Monte Carlo sampler for estimating the moments of the EP tilted distributions. Further, as opposed to EP which has no guarantee of convergence, SNEP can be shown to be convergent, even wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.09327","kind":"arxiv","version":4},"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":"1512.09327","created_at":"2026-05-18T00:35:49.035552+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.09327v4","created_at":"2026-05-18T00:35:49.035552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.09327","created_at":"2026-05-18T00:35:49.035552+00:00"},{"alias_kind":"pith_short_12","alias_value":"QHMN5FGY43FB","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"QHMN5FGY43FBRWHC","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"QHMN5FGY","created_at":"2026-05-18T12:29:37.295048+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/QHMN5FGY43FBRWHC6RSCLU24RR","json":"https://pith.science/pith/QHMN5FGY43FBRWHC6RSCLU24RR.json","graph_json":"https://pith.science/api/pith-number/QHMN5FGY43FBRWHC6RSCLU24RR/graph.json","events_json":"https://pith.science/api/pith-number/QHMN5FGY43FBRWHC6RSCLU24RR/events.json","paper":"https://pith.science/paper/QHMN5FGY"},"agent_actions":{"view_html":"https://pith.science/pith/QHMN5FGY43FBRWHC6RSCLU24RR","download_json":"https://pith.science/pith/QHMN5FGY43FBRWHC6RSCLU24RR.json","view_paper":"https://pith.science/paper/QHMN5FGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.09327&json=true","fetch_graph":"https://pith.science/api/pith-number/QHMN5FGY43FBRWHC6RSCLU24RR/graph.json","fetch_events":"https://pith.science/api/pith-number/QHMN5FGY43FBRWHC6RSCLU24RR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QHMN5FGY43FBRWHC6RSCLU24RR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QHMN5FGY43FBRWHC6RSCLU24RR/action/storage_attestation","attest_author":"https://pith.science/pith/QHMN5FGY43FBRWHC6RSCLU24RR/action/author_attestation","sign_citation":"https://pith.science/pith/QHMN5FGY43FBRWHC6RSCLU24RR/action/citation_signature","submit_replication":"https://pith.science/pith/QHMN5FGY43FBRWHC6RSCLU24RR/action/replication_record"}},"created_at":"2026-05-18T00:35:49.035552+00:00","updated_at":"2026-05-18T00:35:49.035552+00:00"}