{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IEP3GLFWGTNLIMME2CCZRZ6ASD","short_pith_number":"pith:IEP3GLFW","schema_version":"1.0","canonical_sha256":"411fb32cb634dab43184d08598e7c090ca07ebe02100349bca577ee48ed48b77","source":{"kind":"arxiv","id":"1808.00387","version":2},"attestation_state":"computed","paper":{"title":"Just Interpolate: Kernel \"Ridgeless\" Regression Can Generalize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Alexander Rakhlin, Tengyuan Liang","submitted_at":"2018-08-01T15:50:23Z","abstract_excerpt":"In the absence of explicit regularization, Kernel \"Ridgeless\" Regression with nonlinear kernels has the potential to fit the training data perfectly. It has been observed empirically, however, that such interpolated solutions can still generalize well on test data. We isolate a phenomenon of implicit regularization for minimum-norm interpolated solutions which is due to a combination of high dimensionality of the input data, curvature of the kernel function, and favorable geometric properties of the data such as an eigenvalue decay of the empirical covariance and kernel matrices. In addition t"},"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":"1808.00387","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2018-08-01T15:50:23Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"ca15f807787997b905760a3c9b596985d7fea19dcba4e0915a67bdfa2a7d5b0d","abstract_canon_sha256":"90aa0670c7b0a3cad3834f5997a001bd79f61691919a52f4d5b62c3b68afb670"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:21:45.029759Z","signature_b64":"UI1h3cDZkdSHA8M9MBr/h4MdpqWx2k58rFwIMdkCs1S1nuykUY9AoDyfxheDVXukoG3ptjAkcEII5iMRzjY3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"411fb32cb634dab43184d08598e7c090ca07ebe02100349bca577ee48ed48b77","last_reissued_at":"2026-07-05T01:21:45.029280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:21:45.029280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Just Interpolate: Kernel \"Ridgeless\" Regression Can Generalize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Alexander Rakhlin, Tengyuan Liang","submitted_at":"2018-08-01T15:50:23Z","abstract_excerpt":"In the absence of explicit regularization, Kernel \"Ridgeless\" Regression with nonlinear kernels has the potential to fit the training data perfectly. It has been observed empirically, however, that such interpolated solutions can still generalize well on test data. We isolate a phenomenon of implicit regularization for minimum-norm interpolated solutions which is due to a combination of high dimensionality of the input data, curvature of the kernel function, and favorable geometric properties of the data such as an eigenvalue decay of the empirical covariance and kernel matrices. In addition t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.00387","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/1808.00387/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":"1808.00387","created_at":"2026-07-05T01:21:45.029336+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.00387v2","created_at":"2026-07-05T01:21:45.029336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.00387","created_at":"2026-07-05T01:21:45.029336+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEP3GLFWGTNL","created_at":"2026-07-05T01:21:45.029336+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEP3GLFWGTNLIMME","created_at":"2026-07-05T01:21:45.029336+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEP3GLFW","created_at":"2026-07-05T01:21:45.029336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.17412","citing_title":"A Ridge Too Far: Correcting Over-Shrinkage via Negative Regularization","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06314","citing_title":"When Does $\\ell_2$-Boosting Overfit Benignly? High-Dimensional Risk Asymptotics and the $\\ell_1$ Implicit Bias","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06314","citing_title":"When Does $\\ell_2$-Boosting Overfit Benignly? High-Dimensional Risk Asymptotics and the $\\ell_1$ Implicit Bias","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IEP3GLFWGTNLIMME2CCZRZ6ASD","json":"https://pith.science/pith/IEP3GLFWGTNLIMME2CCZRZ6ASD.json","graph_json":"https://pith.science/api/pith-number/IEP3GLFWGTNLIMME2CCZRZ6ASD/graph.json","events_json":"https://pith.science/api/pith-number/IEP3GLFWGTNLIMME2CCZRZ6ASD/events.json","paper":"https://pith.science/paper/IEP3GLFW"},"agent_actions":{"view_html":"https://pith.science/pith/IEP3GLFWGTNLIMME2CCZRZ6ASD","download_json":"https://pith.science/pith/IEP3GLFWGTNLIMME2CCZRZ6ASD.json","view_paper":"https://pith.science/paper/IEP3GLFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.00387&json=true","fetch_graph":"https://pith.science/api/pith-number/IEP3GLFWGTNLIMME2CCZRZ6ASD/graph.json","fetch_events":"https://pith.science/api/pith-number/IEP3GLFWGTNLIMME2CCZRZ6ASD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEP3GLFWGTNLIMME2CCZRZ6ASD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEP3GLFWGTNLIMME2CCZRZ6ASD/action/storage_attestation","attest_author":"https://pith.science/pith/IEP3GLFWGTNLIMME2CCZRZ6ASD/action/author_attestation","sign_citation":"https://pith.science/pith/IEP3GLFWGTNLIMME2CCZRZ6ASD/action/citation_signature","submit_replication":"https://pith.science/pith/IEP3GLFWGTNLIMME2CCZRZ6ASD/action/replication_record"}},"created_at":"2026-07-05T01:21:45.029336+00:00","updated_at":"2026-07-05T01:21:45.029336+00:00"}