{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:DO6A5RQCU6XQ4OM2YFLLLJGZKY","short_pith_number":"pith:DO6A5RQC","schema_version":"1.0","canonical_sha256":"1bbc0ec602a7af0e399ac156b5a4d9561967bb02c8d464c1b0b979cfdeb2865c","source":{"kind":"arxiv","id":"1506.02785","version":1},"attestation_state":"computed","paper":{"title":"On the Error of Random Fourier Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Danica J. Sutherland, Jeff Schneider","submitted_at":"2015-06-09T05:39:02Z","abstract_excerpt":"Kernel methods give powerful, flexible, and theoretically grounded approaches to solving many problems in machine learning. The standard approach, however, requires pairwise evaluations of a kernel function, which can lead to scalability issues for very large datasets. Rahimi and Recht (2007) suggested a popular approach to handling this problem, known as random Fourier features. The quality of this approximation, however, is not well understood. We improve the uniform error bound of that paper, as well as giving novel understandings of the embedding's variance, approximation error, and use in"},"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":"1506.02785","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-09T05:39:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e2792219df122b89db460bab81d4d3bf357b3353426f1d999c151ca97a436040","abstract_canon_sha256":"84b71f2bb3af7363ecf557b3361a3d7a17c7f41d5119165c3b1332276e26efa8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:08.644475Z","signature_b64":"36YY17Yy1/JgyPpzmeskaHdi4BM9T1dKTgRlzrQOQzoS8AUuGiCLGANkXw80IO8H460CB6niItklWFZ+Y3imBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bbc0ec602a7af0e399ac156b5a4d9561967bb02c8d464c1b0b979cfdeb2865c","last_reissued_at":"2026-07-05T02:30:08.643986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:08.643986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Error of Random Fourier Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Danica J. Sutherland, Jeff Schneider","submitted_at":"2015-06-09T05:39:02Z","abstract_excerpt":"Kernel methods give powerful, flexible, and theoretically grounded approaches to solving many problems in machine learning. The standard approach, however, requires pairwise evaluations of a kernel function, which can lead to scalability issues for very large datasets. Rahimi and Recht (2007) suggested a popular approach to handling this problem, known as random Fourier features. The quality of this approximation, however, is not well understood. We improve the uniform error bound of that paper, as well as giving novel understandings of the embedding's variance, approximation error, and use in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02785","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1506.02785/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":"1506.02785","created_at":"2026-07-05T02:30:08.644045+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.02785v1","created_at":"2026-07-05T02:30:08.644045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02785","created_at":"2026-07-05T02:30:08.644045+00:00"},{"alias_kind":"pith_short_12","alias_value":"DO6A5RQCU6XQ","created_at":"2026-07-05T02:30:08.644045+00:00"},{"alias_kind":"pith_short_16","alias_value":"DO6A5RQCU6XQ4OM2","created_at":"2026-07-05T02:30:08.644045+00:00"},{"alias_kind":"pith_short_8","alias_value":"DO6A5RQC","created_at":"2026-07-05T02:30:08.644045+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01080","citing_title":"Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28970","citing_title":"RGLD: Randomized Global-Local Density Estimation for Tabular Anomaly Detection","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DO6A5RQCU6XQ4OM2YFLLLJGZKY","json":"https://pith.science/pith/DO6A5RQCU6XQ4OM2YFLLLJGZKY.json","graph_json":"https://pith.science/api/pith-number/DO6A5RQCU6XQ4OM2YFLLLJGZKY/graph.json","events_json":"https://pith.science/api/pith-number/DO6A5RQCU6XQ4OM2YFLLLJGZKY/events.json","paper":"https://pith.science/paper/DO6A5RQC"},"agent_actions":{"view_html":"https://pith.science/pith/DO6A5RQCU6XQ4OM2YFLLLJGZKY","download_json":"https://pith.science/pith/DO6A5RQCU6XQ4OM2YFLLLJGZKY.json","view_paper":"https://pith.science/paper/DO6A5RQC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.02785&json=true","fetch_graph":"https://pith.science/api/pith-number/DO6A5RQCU6XQ4OM2YFLLLJGZKY/graph.json","fetch_events":"https://pith.science/api/pith-number/DO6A5RQCU6XQ4OM2YFLLLJGZKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DO6A5RQCU6XQ4OM2YFLLLJGZKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DO6A5RQCU6XQ4OM2YFLLLJGZKY/action/storage_attestation","attest_author":"https://pith.science/pith/DO6A5RQCU6XQ4OM2YFLLLJGZKY/action/author_attestation","sign_citation":"https://pith.science/pith/DO6A5RQCU6XQ4OM2YFLLLJGZKY/action/citation_signature","submit_replication":"https://pith.science/pith/DO6A5RQCU6XQ4OM2YFLLLJGZKY/action/replication_record"}},"created_at":"2026-07-05T02:30:08.644045+00:00","updated_at":"2026-07-05T02:30:08.644045+00:00"}