{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6NZ2WI3WAXVS43AFZEZGUFA23J","short_pith_number":"pith:6NZ2WI3W","schema_version":"1.0","canonical_sha256":"f373ab237605eb2e6c05c9326a141ada540c27f4e7a716a8003ad8594242cf9f","source":{"kind":"arxiv","id":"2409.03891","version":1},"attestation_state":"computed","paper":{"title":"Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gal Vardi, Marko Medvedev, Nathan Srebro","submitted_at":"2024-09-05T19:58:58Z","abstract_excerpt":"We consider the overfitting behavior of minimum norm interpolating solutions of Gaussian kernel ridge regression (i.e. kernel ridgeless regression), when the bandwidth or input dimension varies with the sample size. For fixed dimensions, we show that even with varying or tuned bandwidth, the ridgeless solution is never consistent and, at least with large enough noise, always worse than the null predictor. For increasing dimension, we give a generic characterization of the overfitting behavior for any scaling of the dimension with sample size. We use this to provide the first example of benign "},"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":"2409.03891","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-05T19:58:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6d81b47d56218a5e8860f0270bb42582fb2e1f41fc88d0282a301bdf888a9891","abstract_canon_sha256":"93ae634e8652dc58a84f116f4b07fbf80bb69d96bc0df4431b5ae0e39fc331e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:58.688731Z","signature_b64":"G/qU6lSNZ/3BA+oarUHg5j19TwRLhWYMpZ5qEAHenjzaUqHyjE5m+S/VJPYKr4J/Lyr8AJsCVoHAE7tXHAljCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f373ab237605eb2e6c05c9326a141ada540c27f4e7a716a8003ad8594242cf9f","last_reissued_at":"2026-07-05T09:03:58.688377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:58.688377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gal Vardi, Marko Medvedev, Nathan Srebro","submitted_at":"2024-09-05T19:58:58Z","abstract_excerpt":"We consider the overfitting behavior of minimum norm interpolating solutions of Gaussian kernel ridge regression (i.e. kernel ridgeless regression), when the bandwidth or input dimension varies with the sample size. For fixed dimensions, we show that even with varying or tuned bandwidth, the ridgeless solution is never consistent and, at least with large enough noise, always worse than the null predictor. For increasing dimension, we give a generic characterization of the overfitting behavior for any scaling of the dimension with sample size. We use this to provide the first example of benign "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03891","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/2409.03891/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":"2409.03891","created_at":"2026-07-05T09:03:58.688439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.03891v1","created_at":"2026-07-05T09:03:58.688439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03891","created_at":"2026-07-05T09:03:58.688439+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NZ2WI3WAXVS","created_at":"2026-07-05T09:03:58.688439+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NZ2WI3WAXVS43AF","created_at":"2026-07-05T09:03:58.688439+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NZ2WI3W","created_at":"2026-07-05T09:03:58.688439+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11621","citing_title":"A Classical View on Benign Overfitting: The Role of Sample Size","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NZ2WI3WAXVS43AFZEZGUFA23J","json":"https://pith.science/pith/6NZ2WI3WAXVS43AFZEZGUFA23J.json","graph_json":"https://pith.science/api/pith-number/6NZ2WI3WAXVS43AFZEZGUFA23J/graph.json","events_json":"https://pith.science/api/pith-number/6NZ2WI3WAXVS43AFZEZGUFA23J/events.json","paper":"https://pith.science/paper/6NZ2WI3W"},"agent_actions":{"view_html":"https://pith.science/pith/6NZ2WI3WAXVS43AFZEZGUFA23J","download_json":"https://pith.science/pith/6NZ2WI3WAXVS43AFZEZGUFA23J.json","view_paper":"https://pith.science/paper/6NZ2WI3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.03891&json=true","fetch_graph":"https://pith.science/api/pith-number/6NZ2WI3WAXVS43AFZEZGUFA23J/graph.json","fetch_events":"https://pith.science/api/pith-number/6NZ2WI3WAXVS43AFZEZGUFA23J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NZ2WI3WAXVS43AFZEZGUFA23J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NZ2WI3WAXVS43AFZEZGUFA23J/action/storage_attestation","attest_author":"https://pith.science/pith/6NZ2WI3WAXVS43AFZEZGUFA23J/action/author_attestation","sign_citation":"https://pith.science/pith/6NZ2WI3WAXVS43AFZEZGUFA23J/action/citation_signature","submit_replication":"https://pith.science/pith/6NZ2WI3WAXVS43AFZEZGUFA23J/action/replication_record"}},"created_at":"2026-07-05T09:03:58.688439+00:00","updated_at":"2026-07-05T09:03:58.688439+00:00"}