{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Q3J6KQVJ6HXXTPCLCND2V52N43","short_pith_number":"pith:Q3J6KQVJ","schema_version":"1.0","canonical_sha256":"86d3e542a9f1ef79bc4b1347aaf74de6e804b373f277d8aa5395158608160744","source":{"kind":"arxiv","id":"1811.04504","version":2},"attestation_state":"computed","paper":{"title":"SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Mishkin, Didrik Nielsen, Frederik Kunstner, Mark Schmidt, Mohammad Emtiyaz Khan","submitted_at":"2018-11-11T23:18:27Z","abstract_excerpt":"Uncertainty estimation in large deep-learning models is a computationally challenging task, where it is difficult to form even a Gaussian approximation to the posterior distribution. In such situations, existing methods usually resort to a diagonal approximation of the covariance matrix despite, the fact that these matrices are known to result in poor uncertainty estimates. To address this issue, we propose a new stochastic, low-rank, approximate natural-gradient (SLANG) method for variational inference in large, deep models. Our method estimates a \"diagonal plus low-rank\" structure based sole"},"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":"1811.04504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-11T23:18:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0d73aa940a4016cea8cd7e4908882ace4d0ec42fa6ea5157be3826332c597497","abstract_canon_sha256":"bd00a5e3679fb5e470091692958eb6bf5daedc33e5b9cf6ddb87fa7a521c7bf0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:29.214967Z","signature_b64":"VAs9RfcvwzYrw+pyuHyVsO9wvVKVvhrW1XHz/pgdZWpmz8UDhhwS8pENRzVi+4LB4k7lEl2jVNd+Gl8GGwjsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86d3e542a9f1ef79bc4b1347aaf74de6e804b373f277d8aa5395158608160744","last_reissued_at":"2026-05-17T23:56:29.214485Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:29.214485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Mishkin, Didrik Nielsen, Frederik Kunstner, Mark Schmidt, Mohammad Emtiyaz Khan","submitted_at":"2018-11-11T23:18:27Z","abstract_excerpt":"Uncertainty estimation in large deep-learning models is a computationally challenging task, where it is difficult to form even a Gaussian approximation to the posterior distribution. In such situations, existing methods usually resort to a diagonal approximation of the covariance matrix despite, the fact that these matrices are known to result in poor uncertainty estimates. To address this issue, we propose a new stochastic, low-rank, approximate natural-gradient (SLANG) method for variational inference in large, deep models. Our method estimates a \"diagonal plus low-rank\" structure based sole"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.04504","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":"1811.04504","created_at":"2026-05-17T23:56:29.214549+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.04504v2","created_at":"2026-05-17T23:56:29.214549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.04504","created_at":"2026-05-17T23:56:29.214549+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3J6KQVJ6HXX","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3J6KQVJ6HXXTPCL","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3J6KQVJ","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04154","citing_title":"Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11007","citing_title":"RT-Transformer: The Transformer Block as a Spherical State Estimator","ref_index":155,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3J6KQVJ6HXXTPCLCND2V52N43","json":"https://pith.science/pith/Q3J6KQVJ6HXXTPCLCND2V52N43.json","graph_json":"https://pith.science/api/pith-number/Q3J6KQVJ6HXXTPCLCND2V52N43/graph.json","events_json":"https://pith.science/api/pith-number/Q3J6KQVJ6HXXTPCLCND2V52N43/events.json","paper":"https://pith.science/paper/Q3J6KQVJ"},"agent_actions":{"view_html":"https://pith.science/pith/Q3J6KQVJ6HXXTPCLCND2V52N43","download_json":"https://pith.science/pith/Q3J6KQVJ6HXXTPCLCND2V52N43.json","view_paper":"https://pith.science/paper/Q3J6KQVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.04504&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3J6KQVJ6HXXTPCLCND2V52N43/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3J6KQVJ6HXXTPCLCND2V52N43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3J6KQVJ6HXXTPCLCND2V52N43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3J6KQVJ6HXXTPCLCND2V52N43/action/storage_attestation","attest_author":"https://pith.science/pith/Q3J6KQVJ6HXXTPCLCND2V52N43/action/author_attestation","sign_citation":"https://pith.science/pith/Q3J6KQVJ6HXXTPCLCND2V52N43/action/citation_signature","submit_replication":"https://pith.science/pith/Q3J6KQVJ6HXXTPCLCND2V52N43/action/replication_record"}},"created_at":"2026-05-17T23:56:29.214549+00:00","updated_at":"2026-05-17T23:56:29.214549+00:00"}