{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:H4MN3J3Q6IZOHPBPEDIW275WKA","short_pith_number":"pith:H4MN3J3Q","schema_version":"1.0","canonical_sha256":"3f18dda770f232e3bc2f20d16d7fb6501c6c4df35d3780b2b682446bb8d7000b","source":{"kind":"arxiv","id":"1807.01969","version":1},"attestation_state":"computed","paper":{"title":"Variational Bayesian dropout: pitfalls and fixes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander G. de G. Matthews, Jiri Hron, Zoubin Ghahramani","submitted_at":"2018-07-05T12:48:53Z","abstract_excerpt":"Dropout, a stochastic regularisation technique for training of neural networks, has recently been reinterpreted as a specific type of approximate inference algorithm for Bayesian neural networks. The main contribution of the reinterpretation is in providing a theoretical framework useful for analysing and extending the algorithm. We show that the proposed framework suffers from several issues; from undefined or pathological behaviour of the true posterior related to use of improper priors, to an ill-defined variational objective due to singularity of the approximating distribution relative to "},"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":"1807.01969","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-05T12:48:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c499e33c65e58e05674411eaf4a4f0963d108f9a29a92a04cce93ddf6356d321","abstract_canon_sha256":"723d0635d4da91d30b56b8f7ef0451bc3b243030d592b9436608b339f5b41342"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:24.588285Z","signature_b64":"1JPPg64Kb0dI9ZW7KyKmP3XQeXF+NjNrvK0ynp+5neyD2Tr53eJqiPbNyepOVkHtk9autwT0+haWN7XELvd4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f18dda770f232e3bc2f20d16d7fb6501c6c4df35d3780b2b682446bb8d7000b","last_reissued_at":"2026-05-18T00:11:24.587860Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:24.587860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Bayesian dropout: pitfalls and fixes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander G. de G. Matthews, Jiri Hron, Zoubin Ghahramani","submitted_at":"2018-07-05T12:48:53Z","abstract_excerpt":"Dropout, a stochastic regularisation technique for training of neural networks, has recently been reinterpreted as a specific type of approximate inference algorithm for Bayesian neural networks. The main contribution of the reinterpretation is in providing a theoretical framework useful for analysing and extending the algorithm. We show that the proposed framework suffers from several issues; from undefined or pathological behaviour of the true posterior related to use of improper priors, to an ill-defined variational objective due to singularity of the approximating distribution relative to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01969","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":""},"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":"1807.01969","created_at":"2026-05-18T00:11:24.587927+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.01969v1","created_at":"2026-05-18T00:11:24.587927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01969","created_at":"2026-05-18T00:11:24.587927+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4MN3J3Q6IZO","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4MN3J3Q6IZOHPBP","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4MN3J3Q","created_at":"2026-05-18T12:32:28.185984+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/H4MN3J3Q6IZOHPBPEDIW275WKA","json":"https://pith.science/pith/H4MN3J3Q6IZOHPBPEDIW275WKA.json","graph_json":"https://pith.science/api/pith-number/H4MN3J3Q6IZOHPBPEDIW275WKA/graph.json","events_json":"https://pith.science/api/pith-number/H4MN3J3Q6IZOHPBPEDIW275WKA/events.json","paper":"https://pith.science/paper/H4MN3J3Q"},"agent_actions":{"view_html":"https://pith.science/pith/H4MN3J3Q6IZOHPBPEDIW275WKA","download_json":"https://pith.science/pith/H4MN3J3Q6IZOHPBPEDIW275WKA.json","view_paper":"https://pith.science/paper/H4MN3J3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.01969&json=true","fetch_graph":"https://pith.science/api/pith-number/H4MN3J3Q6IZOHPBPEDIW275WKA/graph.json","fetch_events":"https://pith.science/api/pith-number/H4MN3J3Q6IZOHPBPEDIW275WKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4MN3J3Q6IZOHPBPEDIW275WKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4MN3J3Q6IZOHPBPEDIW275WKA/action/storage_attestation","attest_author":"https://pith.science/pith/H4MN3J3Q6IZOHPBPEDIW275WKA/action/author_attestation","sign_citation":"https://pith.science/pith/H4MN3J3Q6IZOHPBPEDIW275WKA/action/citation_signature","submit_replication":"https://pith.science/pith/H4MN3J3Q6IZOHPBPEDIW275WKA/action/replication_record"}},"created_at":"2026-05-18T00:11:24.587927+00:00","updated_at":"2026-05-18T00:11:24.587927+00:00"}