{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M2YDDYV4SRPNDMULN56YEYTQJO","short_pith_number":"pith:M2YDDYV4","schema_version":"1.0","canonical_sha256":"66b031e2bc945ed1b28b6f7d8262704bb6f6d5e6d0967fa513c341b0a562f9ba","source":{"kind":"arxiv","id":"2404.07709","version":2},"attestation_state":"computed","paper":{"title":"A Geometrical Analysis of Kernel Ridge Regression and its Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Georgios Gavrilopoulos, Guillaume Lecu\\'e, Zong Shang","submitted_at":"2024-04-11T12:53:23Z","abstract_excerpt":"We obtain upper bounds for the estimation error of Kernel Ridge Regression (KRR) for all non-negative regularization parameters, offering a geometric perspective on various phenomena in KRR. As applications: 1. We address the multiple descent problem, unifying the proofs of arxiv:1908.10292 and arxiv:1904.12191 for polynomial kernels and we establish multiple descent for the upper bound of estimation error of KRR under sub-Gaussian design and non-asymptotic regimes. 2. For a sub-Gaussian design vector and for non-asymptotic scenario, we prove a one-sided isomorphic version of the Gaussian Equi"},"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":"2404.07709","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2024-04-11T12:53:23Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"05c79116ed5bdf815d9373c22049f21bf82f08e903fe5d280a87157ec7a13dde","abstract_canon_sha256":"9332b305be29f589e04725d631893e05ec745c4397a74db90fbe1c6d9ccfdfe1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:39.777932Z","signature_b64":"yvC1yNJAdNC4APN5xr1/d3AWD3L4IfSXPvBePz/WTFrJoe9jnU2TSz8q+DfXOUaXYjq+irVU04+uLUgldP5LAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66b031e2bc945ed1b28b6f7d8262704bb6f6d5e6d0967fa513c341b0a562f9ba","last_reissued_at":"2026-07-05T09:17:39.777432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:39.777432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Geometrical Analysis of Kernel Ridge Regression and its Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Georgios Gavrilopoulos, Guillaume Lecu\\'e, Zong Shang","submitted_at":"2024-04-11T12:53:23Z","abstract_excerpt":"We obtain upper bounds for the estimation error of Kernel Ridge Regression (KRR) for all non-negative regularization parameters, offering a geometric perspective on various phenomena in KRR. As applications: 1. We address the multiple descent problem, unifying the proofs of arxiv:1908.10292 and arxiv:1904.12191 for polynomial kernels and we establish multiple descent for the upper bound of estimation error of KRR under sub-Gaussian design and non-asymptotic regimes. 2. For a sub-Gaussian design vector and for non-asymptotic scenario, we prove a one-sided isomorphic version of the Gaussian Equi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07709","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/2404.07709/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":"2404.07709","created_at":"2026-07-05T09:17:39.777487+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07709v2","created_at":"2026-07-05T09:17:39.777487+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07709","created_at":"2026-07-05T09:17:39.777487+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2YDDYV4SRPN","created_at":"2026-07-05T09:17:39.777487+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2YDDYV4SRPNDMUL","created_at":"2026-07-05T09:17:39.777487+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2YDDYV4","created_at":"2026-07-05T09:17:39.777487+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.14473","citing_title":"Sharp convergence rates for Spectral methods via the feature space decomposition method","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2YDDYV4SRPNDMULN56YEYTQJO","json":"https://pith.science/pith/M2YDDYV4SRPNDMULN56YEYTQJO.json","graph_json":"https://pith.science/api/pith-number/M2YDDYV4SRPNDMULN56YEYTQJO/graph.json","events_json":"https://pith.science/api/pith-number/M2YDDYV4SRPNDMULN56YEYTQJO/events.json","paper":"https://pith.science/paper/M2YDDYV4"},"agent_actions":{"view_html":"https://pith.science/pith/M2YDDYV4SRPNDMULN56YEYTQJO","download_json":"https://pith.science/pith/M2YDDYV4SRPNDMULN56YEYTQJO.json","view_paper":"https://pith.science/paper/M2YDDYV4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07709&json=true","fetch_graph":"https://pith.science/api/pith-number/M2YDDYV4SRPNDMULN56YEYTQJO/graph.json","fetch_events":"https://pith.science/api/pith-number/M2YDDYV4SRPNDMULN56YEYTQJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2YDDYV4SRPNDMULN56YEYTQJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2YDDYV4SRPNDMULN56YEYTQJO/action/storage_attestation","attest_author":"https://pith.science/pith/M2YDDYV4SRPNDMULN56YEYTQJO/action/author_attestation","sign_citation":"https://pith.science/pith/M2YDDYV4SRPNDMULN56YEYTQJO/action/citation_signature","submit_replication":"https://pith.science/pith/M2YDDYV4SRPNDMULN56YEYTQJO/action/replication_record"}},"created_at":"2026-07-05T09:17:39.777487+00:00","updated_at":"2026-07-05T09:17:39.777487+00:00"}