{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LDVUAYBE2WZOKRQMFOG67Y6DUF","short_pith_number":"pith:LDVUAYBE","schema_version":"1.0","canonical_sha256":"58eb406024d5b2e5460c2b8defe3c3a16cfbdf60e9c1b78aaee7ab2795476788","source":{"kind":"arxiv","id":"2308.15434","version":1},"attestation_state":"computed","paper":{"title":"Random feature approximation for general spectral methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mike Nguyen, Nicole M\\\"ucke","submitted_at":"2023-08-29T16:56:03Z","abstract_excerpt":"Random feature approximation is arguably one of the most popular techniques to speed up kernel methods in large scale algorithms and provides a theoretical approach to the analysis of deep neural networks. We analyze generalization properties for a large class of spectral regularization methods combined with random features, containing kernel methods with implicit regularization such as gradient descent or explicit methods like Tikhonov regularization. For our estimators we obtain optimal learning rates over regularity classes (even for classes that are not included in the reproducing kernel H"},"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":"2308.15434","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-29T16:56:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"614e312528b4348a6d68416058d5aaa7725ee66f26e0745d328f92e63a411d64","abstract_canon_sha256":"6b273ba916251e8a0711d67619e4aa831d33ad827cf622152857974e34f850bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:54.592803Z","signature_b64":"er7CfPtkPl6nWf6iVZz5c9Ns357ylLAseKPRZTjDoFCCXRre+gU2eVhsvYcoZa6m8TzKpnPXDFGkiYaAlqTVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58eb406024d5b2e5460c2b8defe3c3a16cfbdf60e9c1b78aaee7ab2795476788","last_reissued_at":"2026-07-05T06:45:54.592288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:54.592288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random feature approximation for general spectral methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mike Nguyen, Nicole M\\\"ucke","submitted_at":"2023-08-29T16:56:03Z","abstract_excerpt":"Random feature approximation is arguably one of the most popular techniques to speed up kernel methods in large scale algorithms and provides a theoretical approach to the analysis of deep neural networks. We analyze generalization properties for a large class of spectral regularization methods combined with random features, containing kernel methods with implicit regularization such as gradient descent or explicit methods like Tikhonov regularization. For our estimators we obtain optimal learning rates over regularity classes (even for classes that are not included in the reproducing kernel H"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15434","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/2308.15434/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":"2308.15434","created_at":"2026-07-05T06:45:54.592364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.15434v1","created_at":"2026-07-05T06:45:54.592364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15434","created_at":"2026-07-05T06:45:54.592364+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDVUAYBE2WZO","created_at":"2026-07-05T06:45:54.592364+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDVUAYBE2WZOKRQM","created_at":"2026-07-05T06:45:54.592364+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDVUAYBE","created_at":"2026-07-05T06:45:54.592364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06772","citing_title":"Minimax-Optimal Generalization Bounds for Smooth Deep Neural Networks Trained by (Stochastic) Gradient Descent","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06764","citing_title":"Optimal Rates for Generalization of Gradient Descent Methods with Deep Neural Networks","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDVUAYBE2WZOKRQMFOG67Y6DUF","json":"https://pith.science/pith/LDVUAYBE2WZOKRQMFOG67Y6DUF.json","graph_json":"https://pith.science/api/pith-number/LDVUAYBE2WZOKRQMFOG67Y6DUF/graph.json","events_json":"https://pith.science/api/pith-number/LDVUAYBE2WZOKRQMFOG67Y6DUF/events.json","paper":"https://pith.science/paper/LDVUAYBE"},"agent_actions":{"view_html":"https://pith.science/pith/LDVUAYBE2WZOKRQMFOG67Y6DUF","download_json":"https://pith.science/pith/LDVUAYBE2WZOKRQMFOG67Y6DUF.json","view_paper":"https://pith.science/paper/LDVUAYBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.15434&json=true","fetch_graph":"https://pith.science/api/pith-number/LDVUAYBE2WZOKRQMFOG67Y6DUF/graph.json","fetch_events":"https://pith.science/api/pith-number/LDVUAYBE2WZOKRQMFOG67Y6DUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDVUAYBE2WZOKRQMFOG67Y6DUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDVUAYBE2WZOKRQMFOG67Y6DUF/action/storage_attestation","attest_author":"https://pith.science/pith/LDVUAYBE2WZOKRQMFOG67Y6DUF/action/author_attestation","sign_citation":"https://pith.science/pith/LDVUAYBE2WZOKRQMFOG67Y6DUF/action/citation_signature","submit_replication":"https://pith.science/pith/LDVUAYBE2WZOKRQMFOG67Y6DUF/action/replication_record"}},"created_at":"2026-07-05T06:45:54.592364+00:00","updated_at":"2026-07-05T06:45:54.592364+00:00"}