{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RKLF66AKAMJJYYXDSXQBD2ZSWP","short_pith_number":"pith:RKLF66AK","schema_version":"1.0","canonical_sha256":"8a965f780a03129c62e395e011eb32b3ed223fbbe2112693044670194074d841","source":{"kind":"arxiv","id":"2002.09338","version":2},"attestation_state":"computed","paper":{"title":"Debiasing Stochastic Gradient Descent to handle missing values","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Aude Sportisse (LPSM (UMR\\_8001)), Aymeric Dieuleveut (CMAP), Claire Boyer (LPSM UMR 8001, DMA), Julie Josse (CMAP)","submitted_at":"2020-02-21T14:49:24Z","abstract_excerpt":"Stochastic gradient algorithm is a key ingredient of many machine learning methods, particularly appropriate for large-scale learning.However, a major caveat of large data is their incompleteness.We propose an averaged stochastic gradient algorithm handling missing values in linear models. This approach has the merit to be free from the need of any data distribution modeling and to account for heterogeneous missing proportion.In both streaming and finite-sample settings, we prove that this algorithm achieves convergence rate of $\\mathcal{O}(\\frac{1}{n})$ at the iteration $n$, the same as witho"},"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":"2002.09338","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-02-21T14:49:24Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"55351310e5bcb1845d2634e9c1105cdba5f4b2bc7977c60a8bf03829f13cc775","abstract_canon_sha256":"a3d7fdf330c5891a26936d44f1d4895f2895434ea4ad71fa546efcb2519fb4fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:28.005002Z","signature_b64":"ss7Ortl4Nd2GAFJpfK4VrL37XzzuERPmTODQuBDGwKqDbS0Fu3Qpr0kKgvfvGWVewyACD/tF6pRRr2wx8ZE9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a965f780a03129c62e395e011eb32b3ed223fbbe2112693044670194074d841","last_reissued_at":"2026-07-05T01:08:28.004538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:28.004538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Debiasing Stochastic Gradient Descent to handle missing values","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Aude Sportisse (LPSM (UMR\\_8001)), Aymeric Dieuleveut (CMAP), Claire Boyer (LPSM UMR 8001, DMA), Julie Josse (CMAP)","submitted_at":"2020-02-21T14:49:24Z","abstract_excerpt":"Stochastic gradient algorithm is a key ingredient of many machine learning methods, particularly appropriate for large-scale learning.However, a major caveat of large data is their incompleteness.We propose an averaged stochastic gradient algorithm handling missing values in linear models. This approach has the merit to be free from the need of any data distribution modeling and to account for heterogeneous missing proportion.In both streaming and finite-sample settings, we prove that this algorithm achieves convergence rate of $\\mathcal{O}(\\frac{1}{n})$ at the iteration $n$, the same as witho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09338","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/2002.09338/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":"2002.09338","created_at":"2026-07-05T01:08:28.004602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.09338v2","created_at":"2026-07-05T01:08:28.004602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09338","created_at":"2026-07-05T01:08:28.004602+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKLF66AKAMJJ","created_at":"2026-07-05T01:08:28.004602+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKLF66AKAMJJYYXD","created_at":"2026-07-05T01:08:28.004602+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKLF66AK","created_at":"2026-07-05T01:08:28.004602+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/RKLF66AKAMJJYYXDSXQBD2ZSWP","json":"https://pith.science/pith/RKLF66AKAMJJYYXDSXQBD2ZSWP.json","graph_json":"https://pith.science/api/pith-number/RKLF66AKAMJJYYXDSXQBD2ZSWP/graph.json","events_json":"https://pith.science/api/pith-number/RKLF66AKAMJJYYXDSXQBD2ZSWP/events.json","paper":"https://pith.science/paper/RKLF66AK"},"agent_actions":{"view_html":"https://pith.science/pith/RKLF66AKAMJJYYXDSXQBD2ZSWP","download_json":"https://pith.science/pith/RKLF66AKAMJJYYXDSXQBD2ZSWP.json","view_paper":"https://pith.science/paper/RKLF66AK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.09338&json=true","fetch_graph":"https://pith.science/api/pith-number/RKLF66AKAMJJYYXDSXQBD2ZSWP/graph.json","fetch_events":"https://pith.science/api/pith-number/RKLF66AKAMJJYYXDSXQBD2ZSWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKLF66AKAMJJYYXDSXQBD2ZSWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKLF66AKAMJJYYXDSXQBD2ZSWP/action/storage_attestation","attest_author":"https://pith.science/pith/RKLF66AKAMJJYYXDSXQBD2ZSWP/action/author_attestation","sign_citation":"https://pith.science/pith/RKLF66AKAMJJYYXDSXQBD2ZSWP/action/citation_signature","submit_replication":"https://pith.science/pith/RKLF66AKAMJJYYXDSXQBD2ZSWP/action/replication_record"}},"created_at":"2026-07-05T01:08:28.004602+00:00","updated_at":"2026-07-05T01:08:28.004602+00:00"}