{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RSFUNAEIFM3MHZLGMLVOAFSZWS","short_pith_number":"pith:RSFUNAEI","schema_version":"1.0","canonical_sha256":"8c8b4680882b36c3e56662eae01659b4b5ba835e74fdd6921554556d72532958","source":{"kind":"arxiv","id":"2302.01088","version":2},"attestation_state":"computed","paper":{"title":"Sketched Ridgeless Linear Regression: The Role of Downsampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Qiang Sun, Siyue Yang, Xin Chen, Yicheng Zeng","submitted_at":"2023-02-02T13:21:09Z","abstract_excerpt":"Overparametrization often helps improve the generalization performance. This paper presents a dual view of overparametrization suggesting that downsampling may also help generalize. Focusing on the proportional regime $m\\asymp n \\asymp p$, where $m$ represents the sketching size, $n$ is the sample size, and $p$ is the feature dimensionality, we investigate two out-of-sample prediction risks of the sketched ridgeless least square estimator. Our findings challenge conventional beliefs by showing that downsampling does not always harm generalization but can actually improve it in certain cases. W"},"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":"2302.01088","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2023-02-02T13:21:09Z","cross_cats_sorted":["stat.ML","stat.TH"],"title_canon_sha256":"01ded297dfaf7b1ff146621b9b9610e6ca8375ae77535cb085a75468d4314956","abstract_canon_sha256":"9c3cdaeafafd0e3fe0a3599fa62fdb4b008c3949575cf2587969988de2e9de07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:43.790127Z","signature_b64":"dkeEMqqBMHb5t+5TSXRe9gWDBUPBckbM55YO5fMA83ZSu+EzyKkkMn6F2Pt1lGPpVVnYuntDeuYZ79ngdeATBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c8b4680882b36c3e56662eae01659b4b5ba835e74fdd6921554556d72532958","last_reissued_at":"2026-07-05T07:00:43.789607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:43.789607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sketched Ridgeless Linear Regression: The Role of Downsampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Qiang Sun, Siyue Yang, Xin Chen, Yicheng Zeng","submitted_at":"2023-02-02T13:21:09Z","abstract_excerpt":"Overparametrization often helps improve the generalization performance. This paper presents a dual view of overparametrization suggesting that downsampling may also help generalize. Focusing on the proportional regime $m\\asymp n \\asymp p$, where $m$ represents the sketching size, $n$ is the sample size, and $p$ is the feature dimensionality, we investigate two out-of-sample prediction risks of the sketched ridgeless least square estimator. Our findings challenge conventional beliefs by showing that downsampling does not always harm generalization but can actually improve it in certain cases. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01088","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/2302.01088/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":"2302.01088","created_at":"2026-07-05T07:00:43.789685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.01088v2","created_at":"2026-07-05T07:00:43.789685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01088","created_at":"2026-07-05T07:00:43.789685+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSFUNAEIFM3M","created_at":"2026-07-05T07:00:43.789685+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSFUNAEIFM3MHZLG","created_at":"2026-07-05T07:00:43.789685+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSFUNAEI","created_at":"2026-07-05T07:00:43.789685+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/RSFUNAEIFM3MHZLGMLVOAFSZWS","json":"https://pith.science/pith/RSFUNAEIFM3MHZLGMLVOAFSZWS.json","graph_json":"https://pith.science/api/pith-number/RSFUNAEIFM3MHZLGMLVOAFSZWS/graph.json","events_json":"https://pith.science/api/pith-number/RSFUNAEIFM3MHZLGMLVOAFSZWS/events.json","paper":"https://pith.science/paper/RSFUNAEI"},"agent_actions":{"view_html":"https://pith.science/pith/RSFUNAEIFM3MHZLGMLVOAFSZWS","download_json":"https://pith.science/pith/RSFUNAEIFM3MHZLGMLVOAFSZWS.json","view_paper":"https://pith.science/paper/RSFUNAEI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.01088&json=true","fetch_graph":"https://pith.science/api/pith-number/RSFUNAEIFM3MHZLGMLVOAFSZWS/graph.json","fetch_events":"https://pith.science/api/pith-number/RSFUNAEIFM3MHZLGMLVOAFSZWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSFUNAEIFM3MHZLGMLVOAFSZWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSFUNAEIFM3MHZLGMLVOAFSZWS/action/storage_attestation","attest_author":"https://pith.science/pith/RSFUNAEIFM3MHZLGMLVOAFSZWS/action/author_attestation","sign_citation":"https://pith.science/pith/RSFUNAEIFM3MHZLGMLVOAFSZWS/action/citation_signature","submit_replication":"https://pith.science/pith/RSFUNAEIFM3MHZLGMLVOAFSZWS/action/replication_record"}},"created_at":"2026-07-05T07:00:43.789685+00:00","updated_at":"2026-07-05T07:00:43.789685+00:00"}