{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ROITMKBG2VGRJS4ASAPEO3SK2L","short_pith_number":"pith:ROITMKBG","schema_version":"1.0","canonical_sha256":"8b91362826d54d14cb80901e476e4ad2f40cfcec2c31a752130a76401276c6f9","source":{"kind":"arxiv","id":"1907.07504","version":1},"attestation_state":"computed","paper":{"title":"Subspace Inference for Bayesian Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Gordon Wilson, Dmitry Vetrov, Pavel Izmailov, Polina Kirichenko, Timur Garipov, Wesley J. Maddox","submitted_at":"2019-07-17T13:26:07Z","abstract_excerpt":"Bayesian inference was once a gold standard for learning with neural networks, providing accurate full predictive distributions and well calibrated uncertainty. However, scaling Bayesian inference techniques to deep neural networks is challenging due to the high dimensionality of the parameter space. In this paper, we construct low-dimensional subspaces of parameter space, such as the first principal components of the stochastic gradient descent (SGD) trajectory, which contain diverse sets of high performing models. In these subspaces, we are able to apply elliptical slice sampling and variati"},"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":"1907.07504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-17T13:26:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cc4f6c7136ff5386a906585d08f2c9322d1dfc9557643a230c5aa60f529d7c75","abstract_canon_sha256":"8a01ed4f20051c93576183cec1ab03df281854d1ad0da6f972c8d1346322420a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:21.991675Z","signature_b64":"hcA6fsCdLtIb+2e9RHO5KvHYqUyRiTK/KlmIvO7F6l7RTunKO8av1CjqETl31FRrYi12vMmtBCWOxEmUriCmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b91362826d54d14cb80901e476e4ad2f40cfcec2c31a752130a76401276c6f9","last_reissued_at":"2026-05-17T23:40:21.990936Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:21.990936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Subspace Inference for Bayesian Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Gordon Wilson, Dmitry Vetrov, Pavel Izmailov, Polina Kirichenko, Timur Garipov, Wesley J. Maddox","submitted_at":"2019-07-17T13:26:07Z","abstract_excerpt":"Bayesian inference was once a gold standard for learning with neural networks, providing accurate full predictive distributions and well calibrated uncertainty. However, scaling Bayesian inference techniques to deep neural networks is challenging due to the high dimensionality of the parameter space. In this paper, we construct low-dimensional subspaces of parameter space, such as the first principal components of the stochastic gradient descent (SGD) trajectory, which contain diverse sets of high performing models. In these subspaces, we are able to apply elliptical slice sampling and variati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.07504","kind":"arxiv","version":1},"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":"1907.07504","created_at":"2026-05-17T23:40:21.991054+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.07504v1","created_at":"2026-05-17T23:40:21.991054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.07504","created_at":"2026-05-17T23:40:21.991054+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROITMKBG2VGR","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROITMKBG2VGRJS4A","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROITMKBG","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02345","citing_title":"Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROITMKBG2VGRJS4ASAPEO3SK2L","json":"https://pith.science/pith/ROITMKBG2VGRJS4ASAPEO3SK2L.json","graph_json":"https://pith.science/api/pith-number/ROITMKBG2VGRJS4ASAPEO3SK2L/graph.json","events_json":"https://pith.science/api/pith-number/ROITMKBG2VGRJS4ASAPEO3SK2L/events.json","paper":"https://pith.science/paper/ROITMKBG"},"agent_actions":{"view_html":"https://pith.science/pith/ROITMKBG2VGRJS4ASAPEO3SK2L","download_json":"https://pith.science/pith/ROITMKBG2VGRJS4ASAPEO3SK2L.json","view_paper":"https://pith.science/paper/ROITMKBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.07504&json=true","fetch_graph":"https://pith.science/api/pith-number/ROITMKBG2VGRJS4ASAPEO3SK2L/graph.json","fetch_events":"https://pith.science/api/pith-number/ROITMKBG2VGRJS4ASAPEO3SK2L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROITMKBG2VGRJS4ASAPEO3SK2L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROITMKBG2VGRJS4ASAPEO3SK2L/action/storage_attestation","attest_author":"https://pith.science/pith/ROITMKBG2VGRJS4ASAPEO3SK2L/action/author_attestation","sign_citation":"https://pith.science/pith/ROITMKBG2VGRJS4ASAPEO3SK2L/action/citation_signature","submit_replication":"https://pith.science/pith/ROITMKBG2VGRJS4ASAPEO3SK2L/action/replication_record"}},"created_at":"2026-05-17T23:40:21.991054+00:00","updated_at":"2026-05-17T23:40:21.991054+00:00"}