{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZF76BIORBLCDZYW6LLSDTSQF67","short_pith_number":"pith:ZF76BIOR","schema_version":"1.0","canonical_sha256":"c97fe0a1d10ac43ce2de5ae439ca05f7d304da0b2f742474da5d486b150a7571","source":{"kind":"arxiv","id":"2206.00853","version":2},"attestation_state":"computed","paper":{"title":"Masked Bayesian Neural Networks : Computation and Optimality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dongyoon Yang, Ilsang Ohn, Insung Kong, Jongjin Lee, Yongdai Kim","submitted_at":"2022-06-02T02:59:55Z","abstract_excerpt":"As data size and computing power increase, the architectures of deep neural networks (DNNs) have been getting more complex and huge, and thus there is a growing need to simplify such complex and huge DNNs. In this paper, we propose a novel sparse Bayesian neural network (BNN) which searches a good DNN with an appropriate complexity. We employ the masking variables at each node which can turn off some nodes according to the posterior distribution to yield a nodewise sparse DNN. We devise a prior distribution such that the posterior distribution has theoretical optimalities (i.e. minimax optimal"},"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":"2206.00853","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-06-02T02:59:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"be78f7d3df99c51077f19407c3582e9d96f7a49acc372893af37b9dbc43bf89d","abstract_canon_sha256":"995b582dd11fadd543e5afb90b3c4e712a08b66c76e680ae97caa46d95c6b41f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:32.392490Z","signature_b64":"7Z6Qc8+DbSd3Gm8RuHVaa2ljQgkb0CMyVQC2ZDTIAmyIhoHhtSb9TdhqvwPF92QNycFCS9MRPEmPxY69wI1oCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c97fe0a1d10ac43ce2de5ae439ca05f7d304da0b2f742474da5d486b150a7571","last_reissued_at":"2026-07-05T06:12:32.391992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:32.391992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masked Bayesian Neural Networks : Computation and Optimality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dongyoon Yang, Ilsang Ohn, Insung Kong, Jongjin Lee, Yongdai Kim","submitted_at":"2022-06-02T02:59:55Z","abstract_excerpt":"As data size and computing power increase, the architectures of deep neural networks (DNNs) have been getting more complex and huge, and thus there is a growing need to simplify such complex and huge DNNs. In this paper, we propose a novel sparse Bayesian neural network (BNN) which searches a good DNN with an appropriate complexity. We employ the masking variables at each node which can turn off some nodes according to the posterior distribution to yield a nodewise sparse DNN. We devise a prior distribution such that the posterior distribution has theoretical optimalities (i.e. minimax optimal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00853","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.00853/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2206.00853","created_at":"2026-07-05T06:12:32.392053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.00853v2","created_at":"2026-07-05T06:12:32.392053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00853","created_at":"2026-07-05T06:12:32.392053+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZF76BIORBLCD","created_at":"2026-07-05T06:12:32.392053+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZF76BIORBLCDZYW6","created_at":"2026-07-05T06:12:32.392053+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZF76BIOR","created_at":"2026-07-05T06:12:32.392053+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00715","citing_title":"Rate-optimal neural boundary detection from unlabeled noisy images","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZF76BIORBLCDZYW6LLSDTSQF67","json":"https://pith.science/pith/ZF76BIORBLCDZYW6LLSDTSQF67.json","graph_json":"https://pith.science/api/pith-number/ZF76BIORBLCDZYW6LLSDTSQF67/graph.json","events_json":"https://pith.science/api/pith-number/ZF76BIORBLCDZYW6LLSDTSQF67/events.json","paper":"https://pith.science/paper/ZF76BIOR"},"agent_actions":{"view_html":"https://pith.science/pith/ZF76BIORBLCDZYW6LLSDTSQF67","download_json":"https://pith.science/pith/ZF76BIORBLCDZYW6LLSDTSQF67.json","view_paper":"https://pith.science/paper/ZF76BIOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.00853&json=true","fetch_graph":"https://pith.science/api/pith-number/ZF76BIORBLCDZYW6LLSDTSQF67/graph.json","fetch_events":"https://pith.science/api/pith-number/ZF76BIORBLCDZYW6LLSDTSQF67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZF76BIORBLCDZYW6LLSDTSQF67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZF76BIORBLCDZYW6LLSDTSQF67/action/storage_attestation","attest_author":"https://pith.science/pith/ZF76BIORBLCDZYW6LLSDTSQF67/action/author_attestation","sign_citation":"https://pith.science/pith/ZF76BIORBLCDZYW6LLSDTSQF67/action/citation_signature","submit_replication":"https://pith.science/pith/ZF76BIORBLCDZYW6LLSDTSQF67/action/replication_record"}},"created_at":"2026-07-05T06:12:32.392053+00:00","updated_at":"2026-07-05T06:12:32.392053+00:00"}