{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7SI7FJMUVP7E6XFRQIOFV4HEID","short_pith_number":"pith:7SI7FJMU","schema_version":"1.0","canonical_sha256":"fc91f2a594abfe4f5cb1821c5af0e440e9afa8bd6904d5eb066727c0aa15526c","source":{"kind":"arxiv","id":"2312.15995","version":2},"attestation_state":"computed","paper":{"title":"Generalization in Kernel Regression Under Realistic Assumptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Barzilai, Ohad Shamir","submitted_at":"2023-12-26T10:55:20Z","abstract_excerpt":"It is by now well-established that modern over-parameterized models seem to elude the bias-variance tradeoff and generalize well despite overfitting noise. Many recent works attempt to analyze this phenomenon in the relatively tractable setting of kernel regression. However, as we argue in detail, most past works on this topic either make unrealistic assumptions, or focus on a narrow problem setup. This work aims to provide a unified theory to upper bound the excess risk of kernel regression for nearly all common and realistic settings. Specifically, we provide rigorous bounds that hold for co"},"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":"2312.15995","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-26T10:55:20Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ac60f8f869c10b86011a44f0edc56fd640b30e2a58fec17c89b1760b4f169ad9","abstract_canon_sha256":"12e5f6b680cdda0dbf5c54ce2b3c590a174c2ed0e052300ff3f3a078f6bbf7ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:07.556385Z","signature_b64":"EJIoRdbjuaa/6UOwAxlcp5kPeSG0al5AwHlzVQ2JCvkwpxOmqD7TSdUEI3eZ3ZUVgDT9HxBr00jqS9Ggb+LXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc91f2a594abfe4f5cb1821c5af0e440e9afa8bd6904d5eb066727c0aa15526c","last_reissued_at":"2026-07-05T07:47:07.555898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:07.555898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization in Kernel Regression Under Realistic Assumptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Barzilai, Ohad Shamir","submitted_at":"2023-12-26T10:55:20Z","abstract_excerpt":"It is by now well-established that modern over-parameterized models seem to elude the bias-variance tradeoff and generalize well despite overfitting noise. Many recent works attempt to analyze this phenomenon in the relatively tractable setting of kernel regression. However, as we argue in detail, most past works on this topic either make unrealistic assumptions, or focus on a narrow problem setup. This work aims to provide a unified theory to upper bound the excess risk of kernel regression for nearly all common and realistic settings. Specifically, we provide rigorous bounds that hold for co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15995","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/2312.15995/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":"2312.15995","created_at":"2026-07-05T07:47:07.555953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.15995v2","created_at":"2026-07-05T07:47:07.555953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15995","created_at":"2026-07-05T07:47:07.555953+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SI7FJMUVP7E","created_at":"2026-07-05T07:47:07.555953+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SI7FJMUVP7E6XFR","created_at":"2026-07-05T07:47:07.555953+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SI7FJMU","created_at":"2026-07-05T07:47:07.555953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.05576","citing_title":"Tighter Learning Guarantees on Digital Computers via Concentration of Measure on Finite Spaces","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14473","citing_title":"Sharp convergence rates for Spectral methods via the feature space decomposition method","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20294","citing_title":"Alignment-Sensitive Minimax Rates for Spectral Algorithms with Learned Kernels","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14524","citing_title":"Large Dimensional Kernel Ridge Regression: Extending to Product Kernels","ref_index":132,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7SI7FJMUVP7E6XFRQIOFV4HEID","json":"https://pith.science/pith/7SI7FJMUVP7E6XFRQIOFV4HEID.json","graph_json":"https://pith.science/api/pith-number/7SI7FJMUVP7E6XFRQIOFV4HEID/graph.json","events_json":"https://pith.science/api/pith-number/7SI7FJMUVP7E6XFRQIOFV4HEID/events.json","paper":"https://pith.science/paper/7SI7FJMU"},"agent_actions":{"view_html":"https://pith.science/pith/7SI7FJMUVP7E6XFRQIOFV4HEID","download_json":"https://pith.science/pith/7SI7FJMUVP7E6XFRQIOFV4HEID.json","view_paper":"https://pith.science/paper/7SI7FJMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.15995&json=true","fetch_graph":"https://pith.science/api/pith-number/7SI7FJMUVP7E6XFRQIOFV4HEID/graph.json","fetch_events":"https://pith.science/api/pith-number/7SI7FJMUVP7E6XFRQIOFV4HEID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SI7FJMUVP7E6XFRQIOFV4HEID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SI7FJMUVP7E6XFRQIOFV4HEID/action/storage_attestation","attest_author":"https://pith.science/pith/7SI7FJMUVP7E6XFRQIOFV4HEID/action/author_attestation","sign_citation":"https://pith.science/pith/7SI7FJMUVP7E6XFRQIOFV4HEID/action/citation_signature","submit_replication":"https://pith.science/pith/7SI7FJMUVP7E6XFRQIOFV4HEID/action/replication_record"}},"created_at":"2026-07-05T07:47:07.555953+00:00","updated_at":"2026-07-05T07:47:07.555953+00:00"}