{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MVG7FGKWLORP4EDRTJ7DNXE4TE","short_pith_number":"pith:MVG7FGKW","schema_version":"1.0","canonical_sha256":"654df299565ba2fe10719a7e36dc9c99071b951296d73e77a7deeda185dca3d5","source":{"kind":"arxiv","id":"1810.10082","version":4},"attestation_state":"computed","paper":{"title":"A Continuous-Time View of Early Stopping for Least Squares","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alnur Ali, J. Zico Kolter, Ryan J. Tibshirani","submitted_at":"2018-10-23T20:44:16Z","abstract_excerpt":"We study the statistical properties of the iterates generated by gradient descent, applied to the fundamental problem of least squares regression. We take a continuous-time view, i.e., consider infinitesimal step sizes in gradient descent, in which case the iterates form a trajectory called gradient flow. Our primary focus is to compare the risk of gradient flow to that of ridge regression. Under the calibration $t=1/\\lambda$---where $t$ is the time parameter in gradient flow, and $\\lambda$ the tuning parameter in ridge regression---we prove that the risk of gradient flow is no less than 1.69 "},"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":"1810.10082","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-23T20:44:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"969abb4f73b55b9d5bb74735bb1901a5350bf719599d21d69f409b5c53988f22","abstract_canon_sha256":"ae12014fc671f1636df320553c2d8b62f188db7db30780226f8ac4af7a2021c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:51.786607Z","signature_b64":"eX3ka89MMed10dUzU+hCI0iG5yWf0UOteMqPPpqxhqaU/2GI0XL4syIraNW6sTU96fqC2SXyG+RRNVTKsacPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"654df299565ba2fe10719a7e36dc9c99071b951296d73e77a7deeda185dca3d5","last_reissued_at":"2026-05-17T23:52:51.785978Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:51.785978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Continuous-Time View of Early Stopping for Least Squares","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alnur Ali, J. Zico Kolter, Ryan J. Tibshirani","submitted_at":"2018-10-23T20:44:16Z","abstract_excerpt":"We study the statistical properties of the iterates generated by gradient descent, applied to the fundamental problem of least squares regression. We take a continuous-time view, i.e., consider infinitesimal step sizes in gradient descent, in which case the iterates form a trajectory called gradient flow. Our primary focus is to compare the risk of gradient flow to that of ridge regression. Under the calibration $t=1/\\lambda$---where $t$ is the time parameter in gradient flow, and $\\lambda$ the tuning parameter in ridge regression---we prove that the risk of gradient flow is no less than 1.69 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10082","kind":"arxiv","version":4},"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":"1810.10082","created_at":"2026-05-17T23:52:51.786085+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.10082v4","created_at":"2026-05-17T23:52:51.786085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10082","created_at":"2026-05-17T23:52:51.786085+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVG7FGKWLORP","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVG7FGKWLORP4EDR","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVG7FGKW","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09471","citing_title":"The Statistical Cost of Adaptation in Multi-Source Transfer Learning","ref_index":145,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVG7FGKWLORP4EDRTJ7DNXE4TE","json":"https://pith.science/pith/MVG7FGKWLORP4EDRTJ7DNXE4TE.json","graph_json":"https://pith.science/api/pith-number/MVG7FGKWLORP4EDRTJ7DNXE4TE/graph.json","events_json":"https://pith.science/api/pith-number/MVG7FGKWLORP4EDRTJ7DNXE4TE/events.json","paper":"https://pith.science/paper/MVG7FGKW"},"agent_actions":{"view_html":"https://pith.science/pith/MVG7FGKWLORP4EDRTJ7DNXE4TE","download_json":"https://pith.science/pith/MVG7FGKWLORP4EDRTJ7DNXE4TE.json","view_paper":"https://pith.science/paper/MVG7FGKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.10082&json=true","fetch_graph":"https://pith.science/api/pith-number/MVG7FGKWLORP4EDRTJ7DNXE4TE/graph.json","fetch_events":"https://pith.science/api/pith-number/MVG7FGKWLORP4EDRTJ7DNXE4TE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVG7FGKWLORP4EDRTJ7DNXE4TE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVG7FGKWLORP4EDRTJ7DNXE4TE/action/storage_attestation","attest_author":"https://pith.science/pith/MVG7FGKWLORP4EDRTJ7DNXE4TE/action/author_attestation","sign_citation":"https://pith.science/pith/MVG7FGKWLORP4EDRTJ7DNXE4TE/action/citation_signature","submit_replication":"https://pith.science/pith/MVG7FGKWLORP4EDRTJ7DNXE4TE/action/replication_record"}},"created_at":"2026-05-17T23:52:51.786085+00:00","updated_at":"2026-05-17T23:52:51.786085+00:00"}