{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TUXMEFA6DERV5ZN6XZEMLXT2KE","short_pith_number":"pith:TUXMEFA6","schema_version":"1.0","canonical_sha256":"9d2ec2141e19235ee5bebe48c5de7a5110d5cb0f116456ba671d8862843476ea","source":{"kind":"arxiv","id":"2304.12465","version":6},"attestation_state":"computed","paper":{"title":"Robust, randomized preconditioning for kernel ridge regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","stat.ML"],"primary_cat":"math.NA","authors_text":"Ethan N. Epperly, Joel A. Tropp, Mateo D\\'iaz, Robert J. Webber, Zachary Frangella","submitted_at":"2023-04-24T21:48:24Z","abstract_excerpt":"We investigate preconditioned conjugate gradient methods for kernel ridge regression (KRR) problems with a moderate to large number of data points ($10^4 \\leq N \\leq 10^7$). We develop and analyze two randomized preconditioners with complementary guarantees. For full-data KRR, RPCholesky preconditioning requires $O(N^2)$ arithmetic operations to achieve fixed accuracy under sufficiently rapid eigenvalue decay of the kernel matrix. For restricted KRR with $k\\ll N$ centers, KRILL preconditioning requires $O((N+k^2)k\\log k)$ operations with no eigenvalue-decay assumption. Experiments on benchmark"},"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":"2304.12465","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2023-04-24T21:48:24Z","cross_cats_sorted":["cs.NA","stat.ML"],"title_canon_sha256":"79297fc75b24044b6b2eaa3a5ce5e34ad9a987db006e1c7e96d4a1133498f240","abstract_canon_sha256":"51c31d139c09f2f35a56e847ddec6fd91c1cc553b9af8138c2b2e5862574c4b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:24:10.556243Z","signature_b64":"FpY4HwHkOl1/+67LhTa1lfV8dgdbXz+ETgRr7bMpGVdKdvqbiiP+9gbb1+BRmnRyutQikCcoIR9QYc4n0x0tDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d2ec2141e19235ee5bebe48c5de7a5110d5cb0f116456ba671d8862843476ea","last_reissued_at":"2026-08-12T01:24:10.554613Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:24:10.554613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust, randomized preconditioning for kernel ridge regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","stat.ML"],"primary_cat":"math.NA","authors_text":"Ethan N. Epperly, Joel A. Tropp, Mateo D\\'iaz, Robert J. Webber, Zachary Frangella","submitted_at":"2023-04-24T21:48:24Z","abstract_excerpt":"We investigate preconditioned conjugate gradient methods for kernel ridge regression (KRR) problems with a moderate to large number of data points ($10^4 \\leq N \\leq 10^7$). We develop and analyze two randomized preconditioners with complementary guarantees. For full-data KRR, RPCholesky preconditioning requires $O(N^2)$ arithmetic operations to achieve fixed accuracy under sufficiently rapid eigenvalue decay of the kernel matrix. For restricted KRR with $k\\ll N$ centers, KRILL preconditioning requires $O((N+k^2)k\\log k)$ operations with no eigenvalue-decay assumption. Experiments on benchmark"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12465","kind":"arxiv","version":6},"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/2304.12465/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":"2304.12465","created_at":"2026-08-12T01:24:10.558514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.12465v6","created_at":"2026-08-12T01:24:10.558514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12465","created_at":"2026-08-12T01:24:10.558514+00:00"},{"alias_kind":"pith_short_12","alias_value":"TUXMEFA6DERV","created_at":"2026-08-12T01:24:10.558514+00:00"},{"alias_kind":"pith_short_16","alias_value":"TUXMEFA6DERV5ZN6","created_at":"2026-08-12T01:24:10.558514+00:00"},{"alias_kind":"pith_short_8","alias_value":"TUXMEFA6","created_at":"2026-08-12T01:24:10.558514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2510.07929","citing_title":"Scalable Kernel Quantile Regression: A Preconditioned Augmented Lagrangian Method","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25138","citing_title":"Accelerating Regularized Attention Kernel Regression for Spectrum Cartography","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05065","citing_title":"Adaptive LSQR Preconditioning from One Small Sketch","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TUXMEFA6DERV5ZN6XZEMLXT2KE","json":"https://pith.science/pith/TUXMEFA6DERV5ZN6XZEMLXT2KE.json","graph_json":"https://pith.science/api/pith-number/TUXMEFA6DERV5ZN6XZEMLXT2KE/graph.json","events_json":"https://pith.science/api/pith-number/TUXMEFA6DERV5ZN6XZEMLXT2KE/events.json","paper":"https://pith.science/paper/TUXMEFA6"},"agent_actions":{"view_html":"https://pith.science/pith/TUXMEFA6DERV5ZN6XZEMLXT2KE","download_json":"https://pith.science/pith/TUXMEFA6DERV5ZN6XZEMLXT2KE.json","view_paper":"https://pith.science/paper/TUXMEFA6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.12465&json=true","fetch_graph":"https://pith.science/api/pith-number/TUXMEFA6DERV5ZN6XZEMLXT2KE/graph.json","fetch_events":"https://pith.science/api/pith-number/TUXMEFA6DERV5ZN6XZEMLXT2KE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TUXMEFA6DERV5ZN6XZEMLXT2KE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TUXMEFA6DERV5ZN6XZEMLXT2KE/action/storage_attestation","attest_author":"https://pith.science/pith/TUXMEFA6DERV5ZN6XZEMLXT2KE/action/author_attestation","sign_citation":"https://pith.science/pith/TUXMEFA6DERV5ZN6XZEMLXT2KE/action/citation_signature","submit_replication":"https://pith.science/pith/TUXMEFA6DERV5ZN6XZEMLXT2KE/action/replication_record"}},"created_at":"2026-08-12T01:24:10.558514+00:00","updated_at":"2026-08-12T01:24:10.558514+00:00"}