{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4ALBLMDHH5F4YDLXQGUMLFH3XC","short_pith_number":"pith:4ALBLMDH","schema_version":"1.0","canonical_sha256":"e01615b0673f4bcc0d7781a8c594fbb88a2a310fed5aa5b14a7bca53f8758e78","source":{"kind":"arxiv","id":"2102.03594","version":2},"attestation_state":"computed","paper":{"title":"Online nonparametric regression with Sobolev kernels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Alessandro Rudi, Oleksandr Zadorozhnyi, Pierre Gaillard, Sebastien Gerschinovitz","submitted_at":"2021-02-06T15:05:14Z","abstract_excerpt":"In this work we investigate the variation of the online kernelized ridge regression algorithm in the setting of $d-$dimensional adversarial nonparametric regression. We derive the regret upper bounds on the classes of Sobolev spaces $W_{p}^{\\beta}(\\mathcal{X})$, $p\\geq 2, \\beta>\\frac{d}{p}$. The upper bounds are supported by the minimax regret analysis, which reveals that in the cases $\\beta> \\frac{d}{2}$ or $p=\\infty$ these rates are (essentially) optimal. Finally, we compare the performance of the kernelized ridge regression forecaster to the known non-parametric forecasters in terms of the "},"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":"2102.03594","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.ST","submitted_at":"2021-02-06T15:05:14Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"47462a0284a0baaf0ec1008b8d20559ec11715d69f4be2bf2b458e2b32aaa16a","abstract_canon_sha256":"617249142c3b58e50eed529a5985a11f89175895fa3bb097a2797ea2f020adce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:57:14.702779Z","signature_b64":"HtkC9h5wgu/65Gq9s8EDdOiN/VnxOh7MSh8c/tEiznKUmp2NfJBzv/1IX2LvHd2XRs1TAdvMfIts3JYEcnmSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e01615b0673f4bcc0d7781a8c594fbb88a2a310fed5aa5b14a7bca53f8758e78","last_reissued_at":"2026-07-05T02:57:14.702239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:57:14.702239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online nonparametric regression with Sobolev kernels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Alessandro Rudi, Oleksandr Zadorozhnyi, Pierre Gaillard, Sebastien Gerschinovitz","submitted_at":"2021-02-06T15:05:14Z","abstract_excerpt":"In this work we investigate the variation of the online kernelized ridge regression algorithm in the setting of $d-$dimensional adversarial nonparametric regression. We derive the regret upper bounds on the classes of Sobolev spaces $W_{p}^{\\beta}(\\mathcal{X})$, $p\\geq 2, \\beta>\\frac{d}{p}$. The upper bounds are supported by the minimax regret analysis, which reveals that in the cases $\\beta> \\frac{d}{2}$ or $p=\\infty$ these rates are (essentially) optimal. Finally, we compare the performance of the kernelized ridge regression forecaster to the known non-parametric forecasters in terms of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.03594","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/2102.03594/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":"2102.03594","created_at":"2026-07-05T02:57:14.702308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.03594v2","created_at":"2026-07-05T02:57:14.702308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.03594","created_at":"2026-07-05T02:57:14.702308+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ALBLMDHH5F4","created_at":"2026-07-05T02:57:14.702308+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ALBLMDHH5F4YDLX","created_at":"2026-07-05T02:57:14.702308+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ALBLMDH","created_at":"2026-07-05T02:57:14.702308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25021","citing_title":"Dynamic Regret for Online Regression in RKHS via Discounted VAW and Subspace Approximation","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ALBLMDHH5F4YDLXQGUMLFH3XC","json":"https://pith.science/pith/4ALBLMDHH5F4YDLXQGUMLFH3XC.json","graph_json":"https://pith.science/api/pith-number/4ALBLMDHH5F4YDLXQGUMLFH3XC/graph.json","events_json":"https://pith.science/api/pith-number/4ALBLMDHH5F4YDLXQGUMLFH3XC/events.json","paper":"https://pith.science/paper/4ALBLMDH"},"agent_actions":{"view_html":"https://pith.science/pith/4ALBLMDHH5F4YDLXQGUMLFH3XC","download_json":"https://pith.science/pith/4ALBLMDHH5F4YDLXQGUMLFH3XC.json","view_paper":"https://pith.science/paper/4ALBLMDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.03594&json=true","fetch_graph":"https://pith.science/api/pith-number/4ALBLMDHH5F4YDLXQGUMLFH3XC/graph.json","fetch_events":"https://pith.science/api/pith-number/4ALBLMDHH5F4YDLXQGUMLFH3XC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ALBLMDHH5F4YDLXQGUMLFH3XC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ALBLMDHH5F4YDLXQGUMLFH3XC/action/storage_attestation","attest_author":"https://pith.science/pith/4ALBLMDHH5F4YDLXQGUMLFH3XC/action/author_attestation","sign_citation":"https://pith.science/pith/4ALBLMDHH5F4YDLXQGUMLFH3XC/action/citation_signature","submit_replication":"https://pith.science/pith/4ALBLMDHH5F4YDLXQGUMLFH3XC/action/replication_record"}},"created_at":"2026-07-05T02:57:14.702308+00:00","updated_at":"2026-07-05T02:57:14.702308+00:00"}