{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GTPWGZCQLQR4DASJ5S3SYFAWJJ","short_pith_number":"pith:GTPWGZCQ","schema_version":"1.0","canonical_sha256":"34df6364505c23c18249ecb72c14164a434b3502548fd1a88837cca6d36f6e7e","source":{"kind":"arxiv","id":"2509.03151","version":2},"attestation_state":"computed","paper":{"title":"Convergence for adaptive resampling of random Fourier features","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.NA","stat.ML"],"primary_cat":"math.NA","authors_text":"Aku Kammonen, Anamika Pandey, Anders Szepessy, Erik von Schwerin, Mattias Sandberg, Ra\\'ul Tempone, Xin Huang","submitted_at":"2025-09-03T09:03:28Z","abstract_excerpt":"The machine learning random Fourier feature method for data in high dimension is computationally and theoretically attractive since the optimization is based on a convex standard least squares problem and independent sampling of Fourier frequencies. The challenge is to sample the Fourier frequencies well. This work proves convergence of a data adaptive method based on resampling the frequencies asymptotically optimally, as the number of nodes and amount of data tend to infinity. Numerical results based on resampling and adaptive random walk steps together with approximations of the least squar"},"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":"2509.03151","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.NA","submitted_at":"2025-09-03T09:03:28Z","cross_cats_sorted":["cs.NA","stat.ML"],"title_canon_sha256":"3a131e8d7cc6e1e1c2344a637184983e60d6cf319d27761b5519c727c6cabeb6","abstract_canon_sha256":"3a770b5b4f26e8ea94a275b2068487cb2def9d0a8bcef0dc92b8e8f76ec0f768"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:12.974359Z","signature_b64":"BEryY0uONpUmX88LuJaVrePQC7+Mj/3ZkOZMcgL9F5vGfQs1MGgVfIF1vL3JVcg8ULQGlIJjAoGgWV71YF6GCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34df6364505c23c18249ecb72c14164a434b3502548fd1a88837cca6d36f6e7e","last_reissued_at":"2026-05-20T00:04:12.973597Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:12.973597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence for adaptive resampling of random Fourier features","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.NA","stat.ML"],"primary_cat":"math.NA","authors_text":"Aku Kammonen, Anamika Pandey, Anders Szepessy, Erik von Schwerin, Mattias Sandberg, Ra\\'ul Tempone, Xin Huang","submitted_at":"2025-09-03T09:03:28Z","abstract_excerpt":"The machine learning random Fourier feature method for data in high dimension is computationally and theoretically attractive since the optimization is based on a convex standard least squares problem and independent sampling of Fourier frequencies. The challenge is to sample the Fourier frequencies well. This work proves convergence of a data adaptive method based on resampling the frequencies asymptotically optimally, as the number of nodes and amount of data tend to infinity. Numerical results based on resampling and adaptive random walk steps together with approximations of the least squar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03151","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.03151/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":"2509.03151","created_at":"2026-05-20T00:04:12.973711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03151v2","created_at":"2026-05-20T00:04:12.973711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03151","created_at":"2026-05-20T00:04:12.973711+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTPWGZCQLQR4","created_at":"2026-05-20T00:04:12.973711+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTPWGZCQLQR4DASJ","created_at":"2026-05-20T00:04:12.973711+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTPWGZCQ","created_at":"2026-05-20T00:04:12.973711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.19373","citing_title":"Cluster-Based Generalized Additive Models Informed by Random Fourier Features","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTPWGZCQLQR4DASJ5S3SYFAWJJ","json":"https://pith.science/pith/GTPWGZCQLQR4DASJ5S3SYFAWJJ.json","graph_json":"https://pith.science/api/pith-number/GTPWGZCQLQR4DASJ5S3SYFAWJJ/graph.json","events_json":"https://pith.science/api/pith-number/GTPWGZCQLQR4DASJ5S3SYFAWJJ/events.json","paper":"https://pith.science/paper/GTPWGZCQ"},"agent_actions":{"view_html":"https://pith.science/pith/GTPWGZCQLQR4DASJ5S3SYFAWJJ","download_json":"https://pith.science/pith/GTPWGZCQLQR4DASJ5S3SYFAWJJ.json","view_paper":"https://pith.science/paper/GTPWGZCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03151&json=true","fetch_graph":"https://pith.science/api/pith-number/GTPWGZCQLQR4DASJ5S3SYFAWJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GTPWGZCQLQR4DASJ5S3SYFAWJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTPWGZCQLQR4DASJ5S3SYFAWJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTPWGZCQLQR4DASJ5S3SYFAWJJ/action/storage_attestation","attest_author":"https://pith.science/pith/GTPWGZCQLQR4DASJ5S3SYFAWJJ/action/author_attestation","sign_citation":"https://pith.science/pith/GTPWGZCQLQR4DASJ5S3SYFAWJJ/action/citation_signature","submit_replication":"https://pith.science/pith/GTPWGZCQLQR4DASJ5S3SYFAWJJ/action/replication_record"}},"created_at":"2026-05-20T00:04:12.973711+00:00","updated_at":"2026-05-20T00:04:12.973711+00:00"}