{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4OF27MCJDX6YWMJKNSWTMCB25E","short_pith_number":"pith:4OF27MCJ","schema_version":"1.0","canonical_sha256":"e38bafb0491dfd8b312a6cad36083ae90bbcc4fe078fd3c8049c9daf09008ea7","source":{"kind":"arxiv","id":"2205.06798","version":1},"attestation_state":"computed","paper":{"title":"Sharp Asymptotics of Kernel Ridge Regression Beyond the Linear Regime","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hong Hu, Yue M. Lu","submitted_at":"2022-05-13T17:50:54Z","abstract_excerpt":"The generalization performance of kernel ridge regression (KRR) exhibits a multi-phased pattern that crucially depends on the scaling relationship between the sample size $n$ and the underlying dimension $d$. This phenomenon is due to the fact that KRR sequentially learns functions of increasing complexity as the sample size increases; when $d^{k-1}\\ll n\\ll d^{k}$, only polynomials with degree less than $k$ are learned. In this paper, we present sharp asymptotic characterization of the performance of KRR at the critical transition regions with $n \\asymp d^k$, for $k\\in\\mathbb{Z}^{+}$. Our asym"},"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":"2205.06798","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-13T17:50:54Z","cross_cats_sorted":[],"title_canon_sha256":"4a64acc92224704195f7a6dbc53f4af311a62c6bbd7bbeec6375f17510e8905a","abstract_canon_sha256":"07ba0d7d549e0f6c28efd9fbc25f46ef5a5b00fefc92352fd2625d838d0dbdbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:23:02.216048Z","signature_b64":"1l6/w/ocQFpIF6mOxPkU1xWcfOmjto3tilgv1IBoJRl5hp542hqcmsGuwtpO/qpfYHQ64Kv5jX4DZPF4rNSdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e38bafb0491dfd8b312a6cad36083ae90bbcc4fe078fd3c8049c9daf09008ea7","last_reissued_at":"2026-07-05T04:23:02.215524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:23:02.215524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sharp Asymptotics of Kernel Ridge Regression Beyond the Linear Regime","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hong Hu, Yue M. Lu","submitted_at":"2022-05-13T17:50:54Z","abstract_excerpt":"The generalization performance of kernel ridge regression (KRR) exhibits a multi-phased pattern that crucially depends on the scaling relationship between the sample size $n$ and the underlying dimension $d$. This phenomenon is due to the fact that KRR sequentially learns functions of increasing complexity as the sample size increases; when $d^{k-1}\\ll n\\ll d^{k}$, only polynomials with degree less than $k$ are learned. In this paper, we present sharp asymptotic characterization of the performance of KRR at the critical transition regions with $n \\asymp d^k$, for $k\\in\\mathbb{Z}^{+}$. Our asym"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.06798","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/2205.06798/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":"2205.06798","created_at":"2026-07-05T04:23:02.215583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.06798v1","created_at":"2026-07-05T04:23:02.215583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.06798","created_at":"2026-07-05T04:23:02.215583+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OF27MCJDX6Y","created_at":"2026-07-05T04:23:02.215583+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OF27MCJDX6YWMJK","created_at":"2026-07-05T04:23:02.215583+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OF27MCJ","created_at":"2026-07-05T04:23:02.215583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14524","citing_title":"Large Dimensional Kernel Ridge Regression: Extending to Product Kernels","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OF27MCJDX6YWMJKNSWTMCB25E","json":"https://pith.science/pith/4OF27MCJDX6YWMJKNSWTMCB25E.json","graph_json":"https://pith.science/api/pith-number/4OF27MCJDX6YWMJKNSWTMCB25E/graph.json","events_json":"https://pith.science/api/pith-number/4OF27MCJDX6YWMJKNSWTMCB25E/events.json","paper":"https://pith.science/paper/4OF27MCJ"},"agent_actions":{"view_html":"https://pith.science/pith/4OF27MCJDX6YWMJKNSWTMCB25E","download_json":"https://pith.science/pith/4OF27MCJDX6YWMJKNSWTMCB25E.json","view_paper":"https://pith.science/paper/4OF27MCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.06798&json=true","fetch_graph":"https://pith.science/api/pith-number/4OF27MCJDX6YWMJKNSWTMCB25E/graph.json","fetch_events":"https://pith.science/api/pith-number/4OF27MCJDX6YWMJKNSWTMCB25E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OF27MCJDX6YWMJKNSWTMCB25E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OF27MCJDX6YWMJKNSWTMCB25E/action/storage_attestation","attest_author":"https://pith.science/pith/4OF27MCJDX6YWMJKNSWTMCB25E/action/author_attestation","sign_citation":"https://pith.science/pith/4OF27MCJDX6YWMJKNSWTMCB25E/action/citation_signature","submit_replication":"https://pith.science/pith/4OF27MCJDX6YWMJKNSWTMCB25E/action/replication_record"}},"created_at":"2026-07-05T04:23:02.215583+00:00","updated_at":"2026-07-05T04:23:02.215583+00:00"}