{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DNYU3CG35XA7BPSPHIV6KAJCUZ","short_pith_number":"pith:DNYU3CG3","schema_version":"1.0","canonical_sha256":"1b714d88dbedc1f0be4f3a2be50122a6540de9241c25c0f5233f3f569654bf6b","source":{"kind":"arxiv","id":"1810.06943","version":6},"attestation_state":"computed","paper":{"title":"The Deep Weight Prior","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrei Atanov, Arsenii Ashukha, Dmitry Vetrov, Kirill Struminsky, Max Welling","submitted_at":"2018-10-16T11:59:10Z","abstract_excerpt":"Bayesian inference is known to provide a general framework for incorporating prior knowledge or specific properties into machine learning models via carefully choosing a prior distribution. In this work, we propose a new type of prior distributions for convolutional neural networks, deep weight prior (DWP), that exploit generative models to encourage a specific structure of trained convolutional filters e.g., spatial correlations of weights. We define DWP in the form of an implicit distribution and propose a method for variational inference with such type of implicit priors. In experiments, we"},"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":"1810.06943","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2018-10-16T11:59:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3ac7034aa32f4374b815e5b596ddd23ff90bc95cf641fc41a78c1edda753ead6","abstract_canon_sha256":"84e8b6e18546b64d56ec954755b09dcf6c8424e0ab3a6745b5535e659f1fbb52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:41.814924Z","signature_b64":"0GQTY1gTfwTZtXjXmRUtCatwdVEMh5BxkhSm6tAZgEH+c2JcdWrx2LauRD+RYK2XjlNdWCfDJgb2+RVaG1CMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b714d88dbedc1f0be4f3a2be50122a6540de9241c25c0f5233f3f569654bf6b","last_reissued_at":"2026-05-17T23:53:41.814409Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:41.814409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Deep Weight Prior","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrei Atanov, Arsenii Ashukha, Dmitry Vetrov, Kirill Struminsky, Max Welling","submitted_at":"2018-10-16T11:59:10Z","abstract_excerpt":"Bayesian inference is known to provide a general framework for incorporating prior knowledge or specific properties into machine learning models via carefully choosing a prior distribution. In this work, we propose a new type of prior distributions for convolutional neural networks, deep weight prior (DWP), that exploit generative models to encourage a specific structure of trained convolutional filters e.g., spatial correlations of weights. We define DWP in the form of an implicit distribution and propose a method for variational inference with such type of implicit priors. In experiments, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06943","kind":"arxiv","version":6},"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":"1810.06943","created_at":"2026-05-17T23:53:41.814480+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.06943v6","created_at":"2026-05-17T23:53:41.814480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06943","created_at":"2026-05-17T23:53:41.814480+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNYU3CG35XA7","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNYU3CG35XA7BPSP","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNYU3CG3","created_at":"2026-05-18T12:32:19.392346+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/DNYU3CG35XA7BPSPHIV6KAJCUZ","json":"https://pith.science/pith/DNYU3CG35XA7BPSPHIV6KAJCUZ.json","graph_json":"https://pith.science/api/pith-number/DNYU3CG35XA7BPSPHIV6KAJCUZ/graph.json","events_json":"https://pith.science/api/pith-number/DNYU3CG35XA7BPSPHIV6KAJCUZ/events.json","paper":"https://pith.science/paper/DNYU3CG3"},"agent_actions":{"view_html":"https://pith.science/pith/DNYU3CG35XA7BPSPHIV6KAJCUZ","download_json":"https://pith.science/pith/DNYU3CG35XA7BPSPHIV6KAJCUZ.json","view_paper":"https://pith.science/paper/DNYU3CG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.06943&json=true","fetch_graph":"https://pith.science/api/pith-number/DNYU3CG35XA7BPSPHIV6KAJCUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/DNYU3CG35XA7BPSPHIV6KAJCUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNYU3CG35XA7BPSPHIV6KAJCUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNYU3CG35XA7BPSPHIV6KAJCUZ/action/storage_attestation","attest_author":"https://pith.science/pith/DNYU3CG35XA7BPSPHIV6KAJCUZ/action/author_attestation","sign_citation":"https://pith.science/pith/DNYU3CG35XA7BPSPHIV6KAJCUZ/action/citation_signature","submit_replication":"https://pith.science/pith/DNYU3CG35XA7BPSPHIV6KAJCUZ/action/replication_record"}},"created_at":"2026-05-17T23:53:41.814480+00:00","updated_at":"2026-05-17T23:53:41.814480+00:00"}