{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CFVGWUUBPUXXPSFOCMI23BGY47","short_pith_number":"pith:CFVGWUUB","schema_version":"1.0","canonical_sha256":"116a6b52817d2f77c8ae1311ad84d8e7f5279bc5d5a235f619d051b60d27e778","source":{"kind":"arxiv","id":"1903.03571","version":3},"attestation_state":"computed","paper":{"title":"Rates of Convergence for Sparse Variational Gaussian Process Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Carl E. Rasmussen, David R. Burt, Mark van der Wilk","submitted_at":"2019-03-08T17:26:52Z","abstract_excerpt":"Excellent variational approximations to Gaussian process posteriors have been developed which avoid the $\\mathcal{O}\\left(N^3\\right)$ scaling with dataset size $N$. They reduce the computational cost to $\\mathcal{O}\\left(NM^2\\right)$, with $M\\ll N$ being the number of inducing variables, which summarise the process. While the computational cost seems to be linear in $N$, the true complexity of the algorithm depends on how $M$ must increase to ensure a certain quality of approximation. We address this by characterising the behavior of an upper bound on the KL divergence to the posterior. We sho"},"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":"1903.03571","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-08T17:26:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"165e950fc83bc44125403572528a7f5e93a4a32eb1293f086a1dddabe6527366","abstract_canon_sha256":"e2cedcf2641f7154019c19ee0fd1eab4b438a69c17fe001df8c03517d3eecaa6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:12.891286Z","signature_b64":"VLBXwKqdg1ntVqBA4N90ozDuWIMcFIpGmi5GavOH0jwL3B+TzWhcSDLVvJVqt7d0TjCwQF9NvlLhCNWZU3Q3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"116a6b52817d2f77c8ae1311ad84d8e7f5279bc5d5a235f619d051b60d27e778","last_reissued_at":"2026-07-05T00:02:12.890757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:12.890757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rates of Convergence for Sparse Variational Gaussian Process Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Carl E. Rasmussen, David R. Burt, Mark van der Wilk","submitted_at":"2019-03-08T17:26:52Z","abstract_excerpt":"Excellent variational approximations to Gaussian process posteriors have been developed which avoid the $\\mathcal{O}\\left(N^3\\right)$ scaling with dataset size $N$. They reduce the computational cost to $\\mathcal{O}\\left(NM^2\\right)$, with $M\\ll N$ being the number of inducing variables, which summarise the process. While the computational cost seems to be linear in $N$, the true complexity of the algorithm depends on how $M$ must increase to ensure a certain quality of approximation. We address this by characterising the behavior of an upper bound on the KL divergence to the posterior. We sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03571","kind":"arxiv","version":3},"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/1903.03571/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":"1903.03571","created_at":"2026-07-05T00:02:12.890805+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.03571v3","created_at":"2026-07-05T00:02:12.890805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03571","created_at":"2026-07-05T00:02:12.890805+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFVGWUUBPUXX","created_at":"2026-07-05T00:02:12.890805+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFVGWUUBPUXXPSFO","created_at":"2026-07-05T00:02:12.890805+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFVGWUUB","created_at":"2026-07-05T00:02:12.890805+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/CFVGWUUBPUXXPSFOCMI23BGY47","json":"https://pith.science/pith/CFVGWUUBPUXXPSFOCMI23BGY47.json","graph_json":"https://pith.science/api/pith-number/CFVGWUUBPUXXPSFOCMI23BGY47/graph.json","events_json":"https://pith.science/api/pith-number/CFVGWUUBPUXXPSFOCMI23BGY47/events.json","paper":"https://pith.science/paper/CFVGWUUB"},"agent_actions":{"view_html":"https://pith.science/pith/CFVGWUUBPUXXPSFOCMI23BGY47","download_json":"https://pith.science/pith/CFVGWUUBPUXXPSFOCMI23BGY47.json","view_paper":"https://pith.science/paper/CFVGWUUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.03571&json=true","fetch_graph":"https://pith.science/api/pith-number/CFVGWUUBPUXXPSFOCMI23BGY47/graph.json","fetch_events":"https://pith.science/api/pith-number/CFVGWUUBPUXXPSFOCMI23BGY47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFVGWUUBPUXXPSFOCMI23BGY47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFVGWUUBPUXXPSFOCMI23BGY47/action/storage_attestation","attest_author":"https://pith.science/pith/CFVGWUUBPUXXPSFOCMI23BGY47/action/author_attestation","sign_citation":"https://pith.science/pith/CFVGWUUBPUXXPSFOCMI23BGY47/action/citation_signature","submit_replication":"https://pith.science/pith/CFVGWUUBPUXXPSFOCMI23BGY47/action/replication_record"}},"created_at":"2026-07-05T00:02:12.890805+00:00","updated_at":"2026-07-05T00:02:12.890805+00:00"}