{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:TAKM36KZUNKZXLRMW5XU2NTZVB","short_pith_number":"pith:TAKM36KZ","schema_version":"1.0","canonical_sha256":"9814cdf959a3559bae2cb76f4d3679a865c89c922c72e3d8d2085a564a2353f2","source":{"kind":"arxiv","id":"1103.5538","version":2},"attestation_state":"computed","paper":{"title":"Online Learning as Stochastic Approximation of Regularization Paths","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"math.PR","authors_text":"Pierre Tarr\\`es, Yuan Yao","submitted_at":"2011-03-29T03:34:16Z","abstract_excerpt":"In this paper, an online learning algorithm is proposed as sequential stochastic approximation of a regularization path converging to the regression function in reproducing kernel Hilbert spaces (RKHSs). We show that it is possible to produce the best known strong (RKHS norm) convergence rate of batch learning, through a careful choice of the gain or step size sequences, depending on regularity assumptions on the regression function. The corresponding weak (mean square distance) convergence rate is optimal in the sense that it reaches the minimax and individual lower rates in the literature. I"},"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":"1103.5538","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.PR","submitted_at":"2011-03-29T03:34:16Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"37f1ab7caa6e77c4d5fe7b5a72c0f4cd23c4da48a410f65b261d4c394fed747c","abstract_canon_sha256":"eb4750bdc907ddf970cee6e08736f89d30b6a8e6f12e90ce9274d62fd92f04f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:35:54.502565Z","signature_b64":"srWJLZxRnR2qIEI/F32Zd/OUJs2O/jHA5Pi8fgFj/6to+IjWV8D/KIoNDIluF3aHKPBss2W3+9Nxd3SxPmPOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9814cdf959a3559bae2cb76f4d3679a865c89c922c72e3d8d2085a564a2353f2","last_reissued_at":"2026-05-18T03:35:54.501773Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:35:54.501773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Learning as Stochastic Approximation of Regularization Paths","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"math.PR","authors_text":"Pierre Tarr\\`es, Yuan Yao","submitted_at":"2011-03-29T03:34:16Z","abstract_excerpt":"In this paper, an online learning algorithm is proposed as sequential stochastic approximation of a regularization path converging to the regression function in reproducing kernel Hilbert spaces (RKHSs). We show that it is possible to produce the best known strong (RKHS norm) convergence rate of batch learning, through a careful choice of the gain or step size sequences, depending on regularity assumptions on the regression function. The corresponding weak (mean square distance) convergence rate is optimal in the sense that it reaches the minimax and individual lower rates in the literature. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1103.5538","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":""},"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":"1103.5538","created_at":"2026-05-18T03:35:54.501899+00:00"},{"alias_kind":"arxiv_version","alias_value":"1103.5538v2","created_at":"2026-05-18T03:35:54.501899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1103.5538","created_at":"2026-05-18T03:35:54.501899+00:00"},{"alias_kind":"pith_short_12","alias_value":"TAKM36KZUNKZ","created_at":"2026-05-18T12:26:41.206345+00:00"},{"alias_kind":"pith_short_16","alias_value":"TAKM36KZUNKZXLRM","created_at":"2026-05-18T12:26:41.206345+00:00"},{"alias_kind":"pith_short_8","alias_value":"TAKM36KZ","created_at":"2026-05-18T12:26:41.206345+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TAKM36KZUNKZXLRMW5XU2NTZVB","json":"https://pith.science/pith/TAKM36KZUNKZXLRMW5XU2NTZVB.json","graph_json":"https://pith.science/api/pith-number/TAKM36KZUNKZXLRMW5XU2NTZVB/graph.json","events_json":"https://pith.science/api/pith-number/TAKM36KZUNKZXLRMW5XU2NTZVB/events.json","paper":"https://pith.science/paper/TAKM36KZ"},"agent_actions":{"view_html":"https://pith.science/pith/TAKM36KZUNKZXLRMW5XU2NTZVB","download_json":"https://pith.science/pith/TAKM36KZUNKZXLRMW5XU2NTZVB.json","view_paper":"https://pith.science/paper/TAKM36KZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1103.5538&json=true","fetch_graph":"https://pith.science/api/pith-number/TAKM36KZUNKZXLRMW5XU2NTZVB/graph.json","fetch_events":"https://pith.science/api/pith-number/TAKM36KZUNKZXLRMW5XU2NTZVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TAKM36KZUNKZXLRMW5XU2NTZVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TAKM36KZUNKZXLRMW5XU2NTZVB/action/storage_attestation","attest_author":"https://pith.science/pith/TAKM36KZUNKZXLRMW5XU2NTZVB/action/author_attestation","sign_citation":"https://pith.science/pith/TAKM36KZUNKZXLRMW5XU2NTZVB/action/citation_signature","submit_replication":"https://pith.science/pith/TAKM36KZUNKZXLRMW5XU2NTZVB/action/replication_record"}},"created_at":"2026-05-18T03:35:54.501899+00:00","updated_at":"2026-05-18T03:35:54.501899+00:00"}