{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OTUQJ5O5RT7U2M264FGUY7AM74","short_pith_number":"pith:OTUQJ5O5","schema_version":"1.0","canonical_sha256":"74e904f5dd8cff4d335ee14d4c7c0cff2c9d1c057d5c890cf39861f945c4b717","source":{"kind":"arxiv","id":"2301.13585","version":1},"attestation_state":"computed","paper":{"title":"Naive imputation implicitly regularizes high-dimensional linear models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Alexis Ayme (LPSM (UMR\\_8001)), Aymeric Dieuleveut (CMAP), Claire Boyer (LPSM (UMR\\_8001)), Erwan Scornet (CMAP)","submitted_at":"2023-01-31T12:34:10Z","abstract_excerpt":"Two different approaches exist to handle missing values for prediction: either imputation, prior to fitting any predictive algorithms, or dedicated methods able to natively incorporate missing values. While imputation is widely (and easily) use, it is unfortunately biased when low-capacity predictors (such as linear models) are applied afterward. However, in practice, naive imputation exhibits good predictive performance. In this paper, we study the impact of imputation in a high-dimensional linear model with MCAR missing data. We prove that zero imputation performs an implicit regularization "},"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":"2301.13585","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2023-01-31T12:34:10Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"c49b6be37095185f6b606f14b867e1734923e8b74b919aa2a4ac58f41aa1f443","abstract_canon_sha256":"30241fcb832559868091283d2bec047b61f04085ac028959f0d2a3e203efe328"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:16.447989Z","signature_b64":"L2dHAfZaf8gBPVoGm17A2JFvMNNRK4cBemVWyD/QU9EvK1xU8T9lcKXFntgsDSFCmtIZNAAfAoW3B0Czg4hUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74e904f5dd8cff4d335ee14d4c7c0cff2c9d1c057d5c890cf39861f945c4b717","last_reissued_at":"2026-07-05T05:37:16.447496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:16.447496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Naive imputation implicitly regularizes high-dimensional linear models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Alexis Ayme (LPSM (UMR\\_8001)), Aymeric Dieuleveut (CMAP), Claire Boyer (LPSM (UMR\\_8001)), Erwan Scornet (CMAP)","submitted_at":"2023-01-31T12:34:10Z","abstract_excerpt":"Two different approaches exist to handle missing values for prediction: either imputation, prior to fitting any predictive algorithms, or dedicated methods able to natively incorporate missing values. While imputation is widely (and easily) use, it is unfortunately biased when low-capacity predictors (such as linear models) are applied afterward. However, in practice, naive imputation exhibits good predictive performance. In this paper, we study the impact of imputation in a high-dimensional linear model with MCAR missing data. We prove that zero imputation performs an implicit regularization "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13585","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/2301.13585/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":"2301.13585","created_at":"2026-07-05T05:37:16.447559+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13585v1","created_at":"2026-07-05T05:37:16.447559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13585","created_at":"2026-07-05T05:37:16.447559+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTUQJ5O5RT7U","created_at":"2026-07-05T05:37:16.447559+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTUQJ5O5RT7U2M26","created_at":"2026-07-05T05:37:16.447559+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTUQJ5O5","created_at":"2026-07-05T05:37:16.447559+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.16238","citing_title":"Human spatial dynamics for electricity demand forecasting: the case of France during the 2022 energy crisis","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OTUQJ5O5RT7U2M264FGUY7AM74","json":"https://pith.science/pith/OTUQJ5O5RT7U2M264FGUY7AM74.json","graph_json":"https://pith.science/api/pith-number/OTUQJ5O5RT7U2M264FGUY7AM74/graph.json","events_json":"https://pith.science/api/pith-number/OTUQJ5O5RT7U2M264FGUY7AM74/events.json","paper":"https://pith.science/paper/OTUQJ5O5"},"agent_actions":{"view_html":"https://pith.science/pith/OTUQJ5O5RT7U2M264FGUY7AM74","download_json":"https://pith.science/pith/OTUQJ5O5RT7U2M264FGUY7AM74.json","view_paper":"https://pith.science/paper/OTUQJ5O5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13585&json=true","fetch_graph":"https://pith.science/api/pith-number/OTUQJ5O5RT7U2M264FGUY7AM74/graph.json","fetch_events":"https://pith.science/api/pith-number/OTUQJ5O5RT7U2M264FGUY7AM74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTUQJ5O5RT7U2M264FGUY7AM74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTUQJ5O5RT7U2M264FGUY7AM74/action/storage_attestation","attest_author":"https://pith.science/pith/OTUQJ5O5RT7U2M264FGUY7AM74/action/author_attestation","sign_citation":"https://pith.science/pith/OTUQJ5O5RT7U2M264FGUY7AM74/action/citation_signature","submit_replication":"https://pith.science/pith/OTUQJ5O5RT7U2M264FGUY7AM74/action/replication_record"}},"created_at":"2026-07-05T05:37:16.447559+00:00","updated_at":"2026-07-05T05:37:16.447559+00:00"}