{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:S7ICZ4AP542EOWKSIOUTWENCZO","short_pith_number":"pith:S7ICZ4AP","schema_version":"1.0","canonical_sha256":"97d02cf00fef3447595243a93b11a2cb85babd9c38137456edd43780681e2864","source":{"kind":"arxiv","id":"1806.03085","version":2},"attestation_state":"computed","paper":{"title":"A Stein variational Newton method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"stat.ML","authors_text":"Alessio Spantini, Gianluca Detommaso, Robert Scheichl, Tiangang Cui, Youssef Marzouk","submitted_at":"2018-06-08T11:05:29Z","abstract_excerpt":"Stein variational gradient descent (SVGD) was recently proposed as a general purpose nonparametric variational inference algorithm [Liu & Wang, NIPS 2016]: it minimizes the Kullback-Leibler divergence between the target distribution and its approximation by implementing a form of functional gradient descent on a reproducing kernel Hilbert space. In this paper, we accelerate and generalize the SVGD algorithm by including second-order information, thereby approximating a Newton-like iteration in function space. We also show how second-order information can lead to more effective choices of kerne"},"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":"1806.03085","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-08T11:05:29Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"63aae05a6b48f73059f9f4fab1e2211b8791b9a583c781df1a952db52d8566de","abstract_canon_sha256":"792c77f198799a4871dcd90dfaef86a4605425020726889524ea7c08799c2fd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:03.141332Z","signature_b64":"VOis2JXSG/weBm0AcOpbo56oTIjmSU1WM+Q2AZrLQpmkciCMidK615p4m6/QH5DC6UIwvjfJ0vi39I7tEXE1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97d02cf00fef3447595243a93b11a2cb85babd9c38137456edd43780681e2864","last_reissued_at":"2026-05-18T00:02:03.140838Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:03.140838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Stein variational Newton method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"stat.ML","authors_text":"Alessio Spantini, Gianluca Detommaso, Robert Scheichl, Tiangang Cui, Youssef Marzouk","submitted_at":"2018-06-08T11:05:29Z","abstract_excerpt":"Stein variational gradient descent (SVGD) was recently proposed as a general purpose nonparametric variational inference algorithm [Liu & Wang, NIPS 2016]: it minimizes the Kullback-Leibler divergence between the target distribution and its approximation by implementing a form of functional gradient descent on a reproducing kernel Hilbert space. In this paper, we accelerate and generalize the SVGD algorithm by including second-order information, thereby approximating a Newton-like iteration in function space. We also show how second-order information can lead to more effective choices of kerne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03085","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":"1806.03085","created_at":"2026-05-18T00:02:03.140917+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.03085v2","created_at":"2026-05-18T00:02:03.140917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03085","created_at":"2026-05-18T00:02:03.140917+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7ICZ4AP542E","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7ICZ4AP542EOWKS","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7ICZ4AP","created_at":"2026-05-18T12:32:50.500415+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/S7ICZ4AP542EOWKSIOUTWENCZO","json":"https://pith.science/pith/S7ICZ4AP542EOWKSIOUTWENCZO.json","graph_json":"https://pith.science/api/pith-number/S7ICZ4AP542EOWKSIOUTWENCZO/graph.json","events_json":"https://pith.science/api/pith-number/S7ICZ4AP542EOWKSIOUTWENCZO/events.json","paper":"https://pith.science/paper/S7ICZ4AP"},"agent_actions":{"view_html":"https://pith.science/pith/S7ICZ4AP542EOWKSIOUTWENCZO","download_json":"https://pith.science/pith/S7ICZ4AP542EOWKSIOUTWENCZO.json","view_paper":"https://pith.science/paper/S7ICZ4AP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.03085&json=true","fetch_graph":"https://pith.science/api/pith-number/S7ICZ4AP542EOWKSIOUTWENCZO/graph.json","fetch_events":"https://pith.science/api/pith-number/S7ICZ4AP542EOWKSIOUTWENCZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7ICZ4AP542EOWKSIOUTWENCZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7ICZ4AP542EOWKSIOUTWENCZO/action/storage_attestation","attest_author":"https://pith.science/pith/S7ICZ4AP542EOWKSIOUTWENCZO/action/author_attestation","sign_citation":"https://pith.science/pith/S7ICZ4AP542EOWKSIOUTWENCZO/action/citation_signature","submit_replication":"https://pith.science/pith/S7ICZ4AP542EOWKSIOUTWENCZO/action/replication_record"}},"created_at":"2026-05-18T00:02:03.140917+00:00","updated_at":"2026-05-18T00:02:03.140917+00:00"}