{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZEWMWPFVIMD7YSQAY7FGWSLXRP","short_pith_number":"pith:ZEWMWPFV","schema_version":"1.0","canonical_sha256":"c92ccb3cb54307fc4a00c7ca6b49778bd86a6c5cd0018e43576f0e4e9599ddd5","source":{"kind":"arxiv","id":"1910.04355","version":3},"attestation_state":"computed","paper":{"title":"Adaptive Variational Bayesian Inference for Sparse Deep Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Guang Cheng, Jincheng Bai, Qifan Song","submitted_at":"2019-10-10T03:44:09Z","abstract_excerpt":"In this work, we focus on variational Bayesian inference on the sparse Deep Neural Network (DNN) modeled under a class of spike-and-slab priors. Given a pre-specified sparse DNN structure, the corresponding variational posterior contraction rate is characterized that reveals a trade-off between the variational error and the approximation error, which are both determined by the network structural complexity (i.e., depth, width and sparsity). However, the optimal network structure, which strikes the balance of the aforementioned trade-off and yields the best rate, is generally unknown in reality"},"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":"1910.04355","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-10-10T03:44:09Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"749479d0b83e2b6f7e334660672089d1b4c5f462188a71506baadf9226c8105e","abstract_canon_sha256":"2f21f820060fb8d04b5e2675a501af12f6de0a3f4bf04b64dc25091738006b28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:23:55.194844Z","signature_b64":"QL5inUgGI9hfNxWvUXwLBzXufStSvA9HjPrPIJrARzMJFsgQ7kkD1X7YUVhQT8DP0Qwa86wUL7/V+NKEzLYIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c92ccb3cb54307fc4a00c7ca6b49778bd86a6c5cd0018e43576f0e4e9599ddd5","last_reissued_at":"2026-07-05T01:23:55.194375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:23:55.194375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Variational Bayesian Inference for Sparse Deep Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Guang Cheng, Jincheng Bai, Qifan Song","submitted_at":"2019-10-10T03:44:09Z","abstract_excerpt":"In this work, we focus on variational Bayesian inference on the sparse Deep Neural Network (DNN) modeled under a class of spike-and-slab priors. Given a pre-specified sparse DNN structure, the corresponding variational posterior contraction rate is characterized that reveals a trade-off between the variational error and the approximation error, which are both determined by the network structural complexity (i.e., depth, width and sparsity). However, the optimal network structure, which strikes the balance of the aforementioned trade-off and yields the best rate, is generally unknown in reality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.04355","kind":"arxiv","version":3},"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/1910.04355/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":"1910.04355","created_at":"2026-07-05T01:23:55.194435+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.04355v3","created_at":"2026-07-05T01:23:55.194435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.04355","created_at":"2026-07-05T01:23:55.194435+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZEWMWPFVIMD7","created_at":"2026-07-05T01:23:55.194435+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZEWMWPFVIMD7YSQA","created_at":"2026-07-05T01:23:55.194435+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZEWMWPFV","created_at":"2026-07-05T01:23:55.194435+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/ZEWMWPFVIMD7YSQAY7FGWSLXRP","json":"https://pith.science/pith/ZEWMWPFVIMD7YSQAY7FGWSLXRP.json","graph_json":"https://pith.science/api/pith-number/ZEWMWPFVIMD7YSQAY7FGWSLXRP/graph.json","events_json":"https://pith.science/api/pith-number/ZEWMWPFVIMD7YSQAY7FGWSLXRP/events.json","paper":"https://pith.science/paper/ZEWMWPFV"},"agent_actions":{"view_html":"https://pith.science/pith/ZEWMWPFVIMD7YSQAY7FGWSLXRP","download_json":"https://pith.science/pith/ZEWMWPFVIMD7YSQAY7FGWSLXRP.json","view_paper":"https://pith.science/paper/ZEWMWPFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.04355&json=true","fetch_graph":"https://pith.science/api/pith-number/ZEWMWPFVIMD7YSQAY7FGWSLXRP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZEWMWPFVIMD7YSQAY7FGWSLXRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZEWMWPFVIMD7YSQAY7FGWSLXRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZEWMWPFVIMD7YSQAY7FGWSLXRP/action/storage_attestation","attest_author":"https://pith.science/pith/ZEWMWPFVIMD7YSQAY7FGWSLXRP/action/author_attestation","sign_citation":"https://pith.science/pith/ZEWMWPFVIMD7YSQAY7FGWSLXRP/action/citation_signature","submit_replication":"https://pith.science/pith/ZEWMWPFVIMD7YSQAY7FGWSLXRP/action/replication_record"}},"created_at":"2026-07-05T01:23:55.194435+00:00","updated_at":"2026-07-05T01:23:55.194435+00:00"}