{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ENEYXRASJ3VCOMOBXXOTIMSGGL","short_pith_number":"pith:ENEYXRAS","schema_version":"1.0","canonical_sha256":"23498bc4124eea2731c1bddd34324632e9d36b5956a1861bb711da36f38becb6","source":{"kind":"arxiv","id":"1603.04733","version":5},"attestation_state":"computed","paper":{"title":"Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christos Louizos, Max Welling","submitted_at":"2016-03-15T16:01:14Z","abstract_excerpt":"We introduce a variational Bayesian neural network where the parameters are governed via a probability distribution on random matrices. Specifically, we employ a matrix variate Gaussian \\cite{gupta1999matrix} parameter posterior distribution where we explicitly model the covariance among the input and output dimensions of each layer. Furthermore, with approximate covariance matrices we can achieve a more efficient way to represent those correlations that is also cheaper than fully factorized parameter posteriors. We further show that with the \"local reprarametrization trick\" \\cite{kingma2015va"},"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":"1603.04733","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-03-15T16:01:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f77b2150299bdd2f804de38f955193d9b348ddb50dc00b76be84248c21788305","abstract_canon_sha256":"83cf068a6e5c6f06ec8500df4d6a04699eedab6367555a28f2bb7f5ff0aa513b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:58.974790Z","signature_b64":"sdxufbUCI4ORdfBHRw0T2RlNgwlPYtau75HAE8EsurOYLuZJ2pEH1Bvc2UmUK5aV1hhWjUvJTg96vTzvaJK7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23498bc4124eea2731c1bddd34324632e9d36b5956a1861bb711da36f38becb6","last_reissued_at":"2026-05-18T01:11:58.974426Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:58.974426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christos Louizos, Max Welling","submitted_at":"2016-03-15T16:01:14Z","abstract_excerpt":"We introduce a variational Bayesian neural network where the parameters are governed via a probability distribution on random matrices. Specifically, we employ a matrix variate Gaussian \\cite{gupta1999matrix} parameter posterior distribution where we explicitly model the covariance among the input and output dimensions of each layer. Furthermore, with approximate covariance matrices we can achieve a more efficient way to represent those correlations that is also cheaper than fully factorized parameter posteriors. We further show that with the \"local reprarametrization trick\" \\cite{kingma2015va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.04733","kind":"arxiv","version":5},"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":"1603.04733","created_at":"2026-05-18T01:11:58.974489+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.04733v5","created_at":"2026-05-18T01:11:58.974489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.04733","created_at":"2026-05-18T01:11:58.974489+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENEYXRASJ3VC","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENEYXRASJ3VCOMOB","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENEYXRAS","created_at":"2026-05-18T12:30:12.583610+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/ENEYXRASJ3VCOMOBXXOTIMSGGL","json":"https://pith.science/pith/ENEYXRASJ3VCOMOBXXOTIMSGGL.json","graph_json":"https://pith.science/api/pith-number/ENEYXRASJ3VCOMOBXXOTIMSGGL/graph.json","events_json":"https://pith.science/api/pith-number/ENEYXRASJ3VCOMOBXXOTIMSGGL/events.json","paper":"https://pith.science/paper/ENEYXRAS"},"agent_actions":{"view_html":"https://pith.science/pith/ENEYXRASJ3VCOMOBXXOTIMSGGL","download_json":"https://pith.science/pith/ENEYXRASJ3VCOMOBXXOTIMSGGL.json","view_paper":"https://pith.science/paper/ENEYXRAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.04733&json=true","fetch_graph":"https://pith.science/api/pith-number/ENEYXRASJ3VCOMOBXXOTIMSGGL/graph.json","fetch_events":"https://pith.science/api/pith-number/ENEYXRASJ3VCOMOBXXOTIMSGGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENEYXRASJ3VCOMOBXXOTIMSGGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENEYXRASJ3VCOMOBXXOTIMSGGL/action/storage_attestation","attest_author":"https://pith.science/pith/ENEYXRASJ3VCOMOBXXOTIMSGGL/action/author_attestation","sign_citation":"https://pith.science/pith/ENEYXRASJ3VCOMOBXXOTIMSGGL/action/citation_signature","submit_replication":"https://pith.science/pith/ENEYXRASJ3VCOMOBXXOTIMSGGL/action/replication_record"}},"created_at":"2026-05-18T01:11:58.974489+00:00","updated_at":"2026-05-18T01:11:58.974489+00:00"}