{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OW6B6RUPKX3FGNS3V4LUN7SIML","short_pith_number":"pith:OW6B6RUP","schema_version":"1.0","canonical_sha256":"75bc1f468f55f653365baf1746fe4862ec253e939c6e7e35aa26b4e51855f099","source":{"kind":"arxiv","id":"2503.20087","version":2},"attestation_state":"computed","paper":{"title":"Random feature-based double Vovk-Azoury-Warmuth algorithm for online multi-kernel learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dmitry B. Rokhlin, Olga V. Gurtovaya","submitted_at":"2025-03-25T21:57:35Z","abstract_excerpt":"We introduce a novel multi-kernel learning algorithm, VAW$^2$, for online least squares regression in reproducing kernel Hilbert spaces (RKHS). VAW$^2$ leverages random Fourier feature-based functional approximation and the Vovk-Azoury-Warmuth (VAW) method in a two-level procedure: VAW is used to construct expert strategies from random features generated for each kernel at the first level, and then again to combine their predictions at the second level. A theoretical analysis yields a regret bound of $O(T^{1/2}\\ln T)$ in expectation with respect to artificial randomness, when the number of ran"},"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":"2503.20087","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-25T21:57:35Z","cross_cats_sorted":[],"title_canon_sha256":"70837e6b734b2b511d19e4583e1868305df5a7a9ab9b44b835367289246c7db2","abstract_canon_sha256":"8434ad325fda7e6f09d8cc88b2282baa08c1f2616302e7b87a93d826d95508b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:06.482526Z","signature_b64":"XkasvBzV1CN4k2qF4lJfMjTEzRyOG+JByfkortvdMfwjWrLQqkzdapTEJ4VLWN/MvHVQbTqCF16rR2HX4mG3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75bc1f468f55f653365baf1746fe4862ec253e939c6e7e35aa26b4e51855f099","last_reissued_at":"2026-07-05T10:43:06.482014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:06.482014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random feature-based double Vovk-Azoury-Warmuth algorithm for online multi-kernel learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dmitry B. Rokhlin, Olga V. Gurtovaya","submitted_at":"2025-03-25T21:57:35Z","abstract_excerpt":"We introduce a novel multi-kernel learning algorithm, VAW$^2$, for online least squares regression in reproducing kernel Hilbert spaces (RKHS). VAW$^2$ leverages random Fourier feature-based functional approximation and the Vovk-Azoury-Warmuth (VAW) method in a two-level procedure: VAW is used to construct expert strategies from random features generated for each kernel at the first level, and then again to combine their predictions at the second level. A theoretical analysis yields a regret bound of $O(T^{1/2}\\ln T)$ in expectation with respect to artificial randomness, when the number of ran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20087","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/2503.20087/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":"2503.20087","created_at":"2026-07-05T10:43:06.482083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20087v2","created_at":"2026-07-05T10:43:06.482083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20087","created_at":"2026-07-05T10:43:06.482083+00:00"},{"alias_kind":"pith_short_12","alias_value":"OW6B6RUPKX3F","created_at":"2026-07-05T10:43:06.482083+00:00"},{"alias_kind":"pith_short_16","alias_value":"OW6B6RUPKX3FGNS3","created_at":"2026-07-05T10:43:06.482083+00:00"},{"alias_kind":"pith_short_8","alias_value":"OW6B6RUP","created_at":"2026-07-05T10:43:06.482083+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22631","citing_title":"A hierarchical Vovk-Azoury-Warmuth forecaster with discounting for online regression in RKHS","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OW6B6RUPKX3FGNS3V4LUN7SIML","json":"https://pith.science/pith/OW6B6RUPKX3FGNS3V4LUN7SIML.json","graph_json":"https://pith.science/api/pith-number/OW6B6RUPKX3FGNS3V4LUN7SIML/graph.json","events_json":"https://pith.science/api/pith-number/OW6B6RUPKX3FGNS3V4LUN7SIML/events.json","paper":"https://pith.science/paper/OW6B6RUP"},"agent_actions":{"view_html":"https://pith.science/pith/OW6B6RUPKX3FGNS3V4LUN7SIML","download_json":"https://pith.science/pith/OW6B6RUPKX3FGNS3V4LUN7SIML.json","view_paper":"https://pith.science/paper/OW6B6RUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20087&json=true","fetch_graph":"https://pith.science/api/pith-number/OW6B6RUPKX3FGNS3V4LUN7SIML/graph.json","fetch_events":"https://pith.science/api/pith-number/OW6B6RUPKX3FGNS3V4LUN7SIML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OW6B6RUPKX3FGNS3V4LUN7SIML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OW6B6RUPKX3FGNS3V4LUN7SIML/action/storage_attestation","attest_author":"https://pith.science/pith/OW6B6RUPKX3FGNS3V4LUN7SIML/action/author_attestation","sign_citation":"https://pith.science/pith/OW6B6RUPKX3FGNS3V4LUN7SIML/action/citation_signature","submit_replication":"https://pith.science/pith/OW6B6RUPKX3FGNS3V4LUN7SIML/action/replication_record"}},"created_at":"2026-07-05T10:43:06.482083+00:00","updated_at":"2026-07-05T10:43:06.482083+00:00"}