{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:T55UYZYJXFCSVX4RVHNE5IVIPM","short_pith_number":"pith:T55UYZYJ","schema_version":"1.0","canonical_sha256":"9f7b4c6709b9452adf91a9da4ea2a87b283ab0c0f6045d8a3334096abe939a69","source":{"kind":"arxiv","id":"1801.00085","version":2},"attestation_state":"computed","paper":{"title":"Learning Structural Weight Uncertainty for Sequential Decision-Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Changyou Chen, Chunyuan Li, Lawrence Carin, Ruiyi Zhang","submitted_at":"2017-12-30T04:34:34Z","abstract_excerpt":"Learning probability distributions on the weights of neural networks (NNs) has recently proven beneficial in many applications. Bayesian methods, such as Stein variational gradient descent (SVGD), offer an elegant framework to reason about NN model uncertainty. However, by assuming independent Gaussian priors for the individual NN weights (as often applied), SVGD does not impose prior knowledge that there is often structural information (dependence) among weights. We propose efficient posterior learning of structural weight uncertainty, within an SVGD framework, by employing matrix variate Gau"},"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":"1801.00085","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-30T04:34:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"403c6a7106a4ca9d0d6ed87a2f590a102fadb4c291854bea96e7c1daff9b1bc9","abstract_canon_sha256":"a5e0311b56784cfc277cbc184f084bac133d549b638ce14733eb88fc073a0e1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:41.263587Z","signature_b64":"ozUmNudA1aFF7Ga8drXLzmUtm4KoxfLLkPtqK3LpNK+XFevWtbB718z6I8PtiS2hyacC9/xafpsuNFcXNaN+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f7b4c6709b9452adf91a9da4ea2a87b283ab0c0f6045d8a3334096abe939a69","last_reissued_at":"2026-05-18T00:19:41.262812Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:41.262812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Structural Weight Uncertainty for Sequential Decision-Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Changyou Chen, Chunyuan Li, Lawrence Carin, Ruiyi Zhang","submitted_at":"2017-12-30T04:34:34Z","abstract_excerpt":"Learning probability distributions on the weights of neural networks (NNs) has recently proven beneficial in many applications. Bayesian methods, such as Stein variational gradient descent (SVGD), offer an elegant framework to reason about NN model uncertainty. However, by assuming independent Gaussian priors for the individual NN weights (as often applied), SVGD does not impose prior knowledge that there is often structural information (dependence) among weights. We propose efficient posterior learning of structural weight uncertainty, within an SVGD framework, by employing matrix variate Gau"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.00085","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":""},"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":"1801.00085","created_at":"2026-05-18T00:19:41.262947+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.00085v2","created_at":"2026-05-18T00:19:41.262947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00085","created_at":"2026-05-18T00:19:41.262947+00:00"},{"alias_kind":"pith_short_12","alias_value":"T55UYZYJXFCS","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"T55UYZYJXFCSVX4R","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"T55UYZYJ","created_at":"2026-05-18T12:31:43.269735+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/T55UYZYJXFCSVX4RVHNE5IVIPM","json":"https://pith.science/pith/T55UYZYJXFCSVX4RVHNE5IVIPM.json","graph_json":"https://pith.science/api/pith-number/T55UYZYJXFCSVX4RVHNE5IVIPM/graph.json","events_json":"https://pith.science/api/pith-number/T55UYZYJXFCSVX4RVHNE5IVIPM/events.json","paper":"https://pith.science/paper/T55UYZYJ"},"agent_actions":{"view_html":"https://pith.science/pith/T55UYZYJXFCSVX4RVHNE5IVIPM","download_json":"https://pith.science/pith/T55UYZYJXFCSVX4RVHNE5IVIPM.json","view_paper":"https://pith.science/paper/T55UYZYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.00085&json=true","fetch_graph":"https://pith.science/api/pith-number/T55UYZYJXFCSVX4RVHNE5IVIPM/graph.json","fetch_events":"https://pith.science/api/pith-number/T55UYZYJXFCSVX4RVHNE5IVIPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T55UYZYJXFCSVX4RVHNE5IVIPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T55UYZYJXFCSVX4RVHNE5IVIPM/action/storage_attestation","attest_author":"https://pith.science/pith/T55UYZYJXFCSVX4RVHNE5IVIPM/action/author_attestation","sign_citation":"https://pith.science/pith/T55UYZYJXFCSVX4RVHNE5IVIPM/action/citation_signature","submit_replication":"https://pith.science/pith/T55UYZYJXFCSVX4RVHNE5IVIPM/action/replication_record"}},"created_at":"2026-05-18T00:19:41.262947+00:00","updated_at":"2026-05-18T00:19:41.262947+00:00"}