{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QID27I76RMXZR77IZVLE5GT5TT","short_pith_number":"pith:QID27I76","schema_version":"1.0","canonical_sha256":"8207afa3fe8b2f98ffe8cd564e9a7d9cdba1a1697519756812abebe04f15fe1a","source":{"kind":"arxiv","id":"2208.01857","version":1},"attestation_state":"computed","paper":{"title":"The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Difan Zou, Jingfeng Wu, Quanquan Gu, Sham M. Kakade, Vladimir Braverman","submitted_at":"2022-08-03T05:59:49Z","abstract_excerpt":"We study linear regression under covariate shift, where the marginal distribution over the input covariates differs in the source and the target domains, while the conditional distribution of the output given the input covariates is similar across the two domains. We investigate a transfer learning approach with pretraining on the source data and finetuning based on the target data (both conducted by online SGD) for this problem. We establish sharp instance-dependent excess risk upper and lower bounds for this approach. Our bounds suggest that for a large class of linear regression instances, "},"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":"2208.01857","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-03T05:59:49Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"f9b3e6a4aefa5963c37158023649069c9fd7dd56da89a577bea5db37eae65a4e","abstract_canon_sha256":"12ec9cf3f8240733ffb884d7d70655844e173acd8bf9ba498d295d9715b17890"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:50.408592Z","signature_b64":"8+gz2nTdyuLNixff3ALZd2+mhGBeclzV8UpgKEvm0wOxoBm277JfQLRZOAkleK4hvKkqpG6wU+2UKVvKLAM8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8207afa3fe8b2f98ffe8cd564e9a7d9cdba1a1697519756812abebe04f15fe1a","last_reissued_at":"2026-07-05T04:45:50.408189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:50.408189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Difan Zou, Jingfeng Wu, Quanquan Gu, Sham M. Kakade, Vladimir Braverman","submitted_at":"2022-08-03T05:59:49Z","abstract_excerpt":"We study linear regression under covariate shift, where the marginal distribution over the input covariates differs in the source and the target domains, while the conditional distribution of the output given the input covariates is similar across the two domains. We investigate a transfer learning approach with pretraining on the source data and finetuning based on the target data (both conducted by online SGD) for this problem. We establish sharp instance-dependent excess risk upper and lower bounds for this approach. Our bounds suggest that for a large class of linear regression instances, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.01857","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/2208.01857/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":"2208.01857","created_at":"2026-07-05T04:45:50.408242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.01857v1","created_at":"2026-07-05T04:45:50.408242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.01857","created_at":"2026-07-05T04:45:50.408242+00:00"},{"alias_kind":"pith_short_12","alias_value":"QID27I76RMXZ","created_at":"2026-07-05T04:45:50.408242+00:00"},{"alias_kind":"pith_short_16","alias_value":"QID27I76RMXZR77I","created_at":"2026-07-05T04:45:50.408242+00:00"},{"alias_kind":"pith_short_8","alias_value":"QID27I76","created_at":"2026-07-05T04:45:50.408242+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/QID27I76RMXZR77IZVLE5GT5TT","json":"https://pith.science/pith/QID27I76RMXZR77IZVLE5GT5TT.json","graph_json":"https://pith.science/api/pith-number/QID27I76RMXZR77IZVLE5GT5TT/graph.json","events_json":"https://pith.science/api/pith-number/QID27I76RMXZR77IZVLE5GT5TT/events.json","paper":"https://pith.science/paper/QID27I76"},"agent_actions":{"view_html":"https://pith.science/pith/QID27I76RMXZR77IZVLE5GT5TT","download_json":"https://pith.science/pith/QID27I76RMXZR77IZVLE5GT5TT.json","view_paper":"https://pith.science/paper/QID27I76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.01857&json=true","fetch_graph":"https://pith.science/api/pith-number/QID27I76RMXZR77IZVLE5GT5TT/graph.json","fetch_events":"https://pith.science/api/pith-number/QID27I76RMXZR77IZVLE5GT5TT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QID27I76RMXZR77IZVLE5GT5TT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QID27I76RMXZR77IZVLE5GT5TT/action/storage_attestation","attest_author":"https://pith.science/pith/QID27I76RMXZR77IZVLE5GT5TT/action/author_attestation","sign_citation":"https://pith.science/pith/QID27I76RMXZR77IZVLE5GT5TT/action/citation_signature","submit_replication":"https://pith.science/pith/QID27I76RMXZR77IZVLE5GT5TT/action/replication_record"}},"created_at":"2026-07-05T04:45:50.408242+00:00","updated_at":"2026-07-05T04:45:50.408242+00:00"}