{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RXGKAWIVUZMTMNCDE4IEEC3I2U","short_pith_number":"pith:RXGKAWIV","schema_version":"1.0","canonical_sha256":"8dcca05915a6593634432710420b68d52dd2e015a0a1b134a98eb380401615a2","source":{"kind":"arxiv","id":"1908.04847","version":2},"attestation_state":"computed","paper":{"title":"Convergence Rates of Variational Inference in Sparse Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Badr-Eddine Ch\\'erief-Abdellatif","submitted_at":"2019-08-09T18:50:09Z","abstract_excerpt":"Variational inference is becoming more and more popular for approximating intractable posterior distributions in Bayesian statistics and machine learning. Meanwhile, a few recent works have provided theoretical justification and new insights on deep neural networks for estimating smooth functions in usual settings such as nonparametric regression. In this paper, we show that variational inference for sparse deep learning retains the same generalization properties than exact Bayesian inference. In particular, we highlight the connection between estimation and approximation theories via the clas"},"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":"1908.04847","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-08-09T18:50:09Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"6e0834a4081f8ab769aff010133109b7e61cb739fd74305c12875c560bcaf68c","abstract_canon_sha256":"1b4231f8a71ebd5fd10e80a255992f5630d937378b5476b532dcf61847785b27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:39.875198Z","signature_b64":"UB29MIyHFzl7y/LUbOZA3UrLZ/VPiZb+2Gke1UGnaFJKquVnF7WNMl01at0w35YfcWzV5apu4kzkM2o7u1biDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dcca05915a6593634432710420b68d52dd2e015a0a1b134a98eb380401615a2","last_reissued_at":"2026-07-05T00:02:39.874832Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:39.874832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence Rates of Variational Inference in Sparse Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Badr-Eddine Ch\\'erief-Abdellatif","submitted_at":"2019-08-09T18:50:09Z","abstract_excerpt":"Variational inference is becoming more and more popular for approximating intractable posterior distributions in Bayesian statistics and machine learning. Meanwhile, a few recent works have provided theoretical justification and new insights on deep neural networks for estimating smooth functions in usual settings such as nonparametric regression. In this paper, we show that variational inference for sparse deep learning retains the same generalization properties than exact Bayesian inference. In particular, we highlight the connection between estimation and approximation theories via the clas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04847","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/1908.04847/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":"1908.04847","created_at":"2026-07-05T00:02:39.874887+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.04847v2","created_at":"2026-07-05T00:02:39.874887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04847","created_at":"2026-07-05T00:02:39.874887+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXGKAWIVUZMT","created_at":"2026-07-05T00:02:39.874887+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXGKAWIVUZMTMNCD","created_at":"2026-07-05T00:02:39.874887+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXGKAWIV","created_at":"2026-07-05T00:02:39.874887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11773","citing_title":"Can Bayesian Neural Networks Make Confident Predictions?","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RXGKAWIVUZMTMNCDE4IEEC3I2U","json":"https://pith.science/pith/RXGKAWIVUZMTMNCDE4IEEC3I2U.json","graph_json":"https://pith.science/api/pith-number/RXGKAWIVUZMTMNCDE4IEEC3I2U/graph.json","events_json":"https://pith.science/api/pith-number/RXGKAWIVUZMTMNCDE4IEEC3I2U/events.json","paper":"https://pith.science/paper/RXGKAWIV"},"agent_actions":{"view_html":"https://pith.science/pith/RXGKAWIVUZMTMNCDE4IEEC3I2U","download_json":"https://pith.science/pith/RXGKAWIVUZMTMNCDE4IEEC3I2U.json","view_paper":"https://pith.science/paper/RXGKAWIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.04847&json=true","fetch_graph":"https://pith.science/api/pith-number/RXGKAWIVUZMTMNCDE4IEEC3I2U/graph.json","fetch_events":"https://pith.science/api/pith-number/RXGKAWIVUZMTMNCDE4IEEC3I2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXGKAWIVUZMTMNCDE4IEEC3I2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXGKAWIVUZMTMNCDE4IEEC3I2U/action/storage_attestation","attest_author":"https://pith.science/pith/RXGKAWIVUZMTMNCDE4IEEC3I2U/action/author_attestation","sign_citation":"https://pith.science/pith/RXGKAWIVUZMTMNCDE4IEEC3I2U/action/citation_signature","submit_replication":"https://pith.science/pith/RXGKAWIVUZMTMNCDE4IEEC3I2U/action/replication_record"}},"created_at":"2026-07-05T00:02:39.874887+00:00","updated_at":"2026-07-05T00:02:39.874887+00:00"}