{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:F3V6626XALOOYP7KPGI5Z652DM","short_pith_number":"pith:F3V6626X","schema_version":"1.0","canonical_sha256":"2eebef6bd702dcec3fea7991dcfbba1b15e019aa4ce4f037131b75cb1c53ed79","source":{"kind":"arxiv","id":"1903.12297","version":1},"attestation_state":"computed","paper":{"title":"An analysis of the cost of hyper-parameter selection via split-sample validation, with applications to penalized regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jean Feng, Noah Simon","submitted_at":"2019-03-28T23:04:43Z","abstract_excerpt":"In the regression setting, given a set of hyper-parameters, a model-estimation procedure constructs a model from training data. The optimal hyper-parameters that minimize generalization error of the model are usually unknown. In practice they are often estimated using split-sample validation. Up to now, there is an open question regarding how the generalization error of the selected model grows with the number of hyper-parameters to be estimated. To answer this question, we establish finite-sample oracle inequalities for selection based on a single training/test split and based on cross-valida"},"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":"1903.12297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2019-03-28T23:04:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"906e5d56208f62271774b69361b9b7e21d875d1e48056278e874cc6f53361238","abstract_canon_sha256":"611fa9e06734289306b898cf2cb8a9ab903d72904c170c3b34990e80f1e33b1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:54.389590Z","signature_b64":"7KKCcfo4fitJKvU2B4WGPF1lBVIGZj4TPZy5fwBAUM/wY4s4BLq9IdKCFuFEudSkAECcVZfCtK4vSmdHWdVNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eebef6bd702dcec3fea7991dcfbba1b15e019aa4ce4f037131b75cb1c53ed79","last_reissued_at":"2026-05-17T23:49:54.389138Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:54.389138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An analysis of the cost of hyper-parameter selection via split-sample validation, with applications to penalized regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jean Feng, Noah Simon","submitted_at":"2019-03-28T23:04:43Z","abstract_excerpt":"In the regression setting, given a set of hyper-parameters, a model-estimation procedure constructs a model from training data. The optimal hyper-parameters that minimize generalization error of the model are usually unknown. In practice they are often estimated using split-sample validation. Up to now, there is an open question regarding how the generalization error of the selected model grows with the number of hyper-parameters to be estimated. To answer this question, we establish finite-sample oracle inequalities for selection based on a single training/test split and based on cross-valida"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.12297","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":""},"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":"1903.12297","created_at":"2026-05-17T23:49:54.389203+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.12297v1","created_at":"2026-05-17T23:49:54.389203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.12297","created_at":"2026-05-17T23:49:54.389203+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3V6626XALOO","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3V6626XALOOYP7K","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3V6626X","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F3V6626XALOOYP7KPGI5Z652DM","json":"https://pith.science/pith/F3V6626XALOOYP7KPGI5Z652DM.json","graph_json":"https://pith.science/api/pith-number/F3V6626XALOOYP7KPGI5Z652DM/graph.json","events_json":"https://pith.science/api/pith-number/F3V6626XALOOYP7KPGI5Z652DM/events.json","paper":"https://pith.science/paper/F3V6626X"},"agent_actions":{"view_html":"https://pith.science/pith/F3V6626XALOOYP7KPGI5Z652DM","download_json":"https://pith.science/pith/F3V6626XALOOYP7KPGI5Z652DM.json","view_paper":"https://pith.science/paper/F3V6626X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.12297&json=true","fetch_graph":"https://pith.science/api/pith-number/F3V6626XALOOYP7KPGI5Z652DM/graph.json","fetch_events":"https://pith.science/api/pith-number/F3V6626XALOOYP7KPGI5Z652DM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3V6626XALOOYP7KPGI5Z652DM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3V6626XALOOYP7KPGI5Z652DM/action/storage_attestation","attest_author":"https://pith.science/pith/F3V6626XALOOYP7KPGI5Z652DM/action/author_attestation","sign_citation":"https://pith.science/pith/F3V6626XALOOYP7KPGI5Z652DM/action/citation_signature","submit_replication":"https://pith.science/pith/F3V6626XALOOYP7KPGI5Z652DM/action/replication_record"}},"created_at":"2026-05-17T23:49:54.389203+00:00","updated_at":"2026-05-17T23:49:54.389203+00:00"}