{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CDMM55UYPY4STG4EIIVOHC3YYU","short_pith_number":"pith:CDMM55UY","schema_version":"1.0","canonical_sha256":"10d8cef6987e39299b84422ae38b78c52fe48b69706e8832a58db21766b2ef3e","source":{"kind":"arxiv","id":"1810.05471","version":3},"attestation_state":"computed","paper":{"title":"Safe Grid Search with Optimal Complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Eugene Ndiaye, Ichiro Takeuchi, Joseph Salmon, Olivier Fercoq, Tam Le","submitted_at":"2018-10-12T12:16:52Z","abstract_excerpt":"Popular machine learning estimators involve regularization parameters that can be challenging to tune, and standard strategies rely on grid search for this task. In this paper, we revisit the techniques of approximating the regularization path up to predefined tolerance $\\epsilon$ in a unified framework and show that its complexity is $O(1/\\sqrt[d]{\\epsilon})$ for uniformly convex loss of order $d \\geq 2$ and $O(1/\\sqrt{\\epsilon})$ for Generalized Self-Concordant functions. This framework encompasses least-squares but also logistic regression, a case that as far as we know was not handled as p"},"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":"1810.05471","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-12T12:16:52Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"720cb74f11fd578383ffbaa04e4b3666ebfdcf291ef167376270f7c2a6dd8d6a","abstract_canon_sha256":"b1629d4bc17d7aa620d80fe1fff68a6814b98049299c1cee07022c5ff858c018"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:04.367443Z","signature_b64":"mOXqq0UxQwVJ/CFcZlwUfZ31YU52bL3gucYcVD+FL5EepLs1XlaIxirR/vz47fD414Ks2Jtu6jX8WYom/8zYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10d8cef6987e39299b84422ae38b78c52fe48b69706e8832a58db21766b2ef3e","last_reissued_at":"2026-05-17T23:45:04.366771Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:04.366771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Grid Search with Optimal Complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Eugene Ndiaye, Ichiro Takeuchi, Joseph Salmon, Olivier Fercoq, Tam Le","submitted_at":"2018-10-12T12:16:52Z","abstract_excerpt":"Popular machine learning estimators involve regularization parameters that can be challenging to tune, and standard strategies rely on grid search for this task. In this paper, we revisit the techniques of approximating the regularization path up to predefined tolerance $\\epsilon$ in a unified framework and show that its complexity is $O(1/\\sqrt[d]{\\epsilon})$ for uniformly convex loss of order $d \\geq 2$ and $O(1/\\sqrt{\\epsilon})$ for Generalized Self-Concordant functions. This framework encompasses least-squares but also logistic regression, a case that as far as we know was not handled as p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05471","kind":"arxiv","version":3},"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":"1810.05471","created_at":"2026-05-17T23:45:04.366885+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.05471v3","created_at":"2026-05-17T23:45:04.366885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05471","created_at":"2026-05-17T23:45:04.366885+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDMM55UYPY4S","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDMM55UYPY4STG4E","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDMM55UY","created_at":"2026-05-18T12:32:16.446611+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/CDMM55UYPY4STG4EIIVOHC3YYU","json":"https://pith.science/pith/CDMM55UYPY4STG4EIIVOHC3YYU.json","graph_json":"https://pith.science/api/pith-number/CDMM55UYPY4STG4EIIVOHC3YYU/graph.json","events_json":"https://pith.science/api/pith-number/CDMM55UYPY4STG4EIIVOHC3YYU/events.json","paper":"https://pith.science/paper/CDMM55UY"},"agent_actions":{"view_html":"https://pith.science/pith/CDMM55UYPY4STG4EIIVOHC3YYU","download_json":"https://pith.science/pith/CDMM55UYPY4STG4EIIVOHC3YYU.json","view_paper":"https://pith.science/paper/CDMM55UY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.05471&json=true","fetch_graph":"https://pith.science/api/pith-number/CDMM55UYPY4STG4EIIVOHC3YYU/graph.json","fetch_events":"https://pith.science/api/pith-number/CDMM55UYPY4STG4EIIVOHC3YYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDMM55UYPY4STG4EIIVOHC3YYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDMM55UYPY4STG4EIIVOHC3YYU/action/storage_attestation","attest_author":"https://pith.science/pith/CDMM55UYPY4STG4EIIVOHC3YYU/action/author_attestation","sign_citation":"https://pith.science/pith/CDMM55UYPY4STG4EIIVOHC3YYU/action/citation_signature","submit_replication":"https://pith.science/pith/CDMM55UYPY4STG4EIIVOHC3YYU/action/replication_record"}},"created_at":"2026-05-17T23:45:04.366885+00:00","updated_at":"2026-05-17T23:45:04.366885+00:00"}