{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EC62FXLUPHIPLXRY4D5PHSLAUG","short_pith_number":"pith:EC62FXLU","schema_version":"1.0","canonical_sha256":"20bda2dd7479d0f5de38e0faf3c960a18e8ca01489f1966c51042f7de24a1207","source":{"kind":"arxiv","id":"2203.00953","version":4},"attestation_state":"computed","paper":{"title":"Computationally Efficient and Statistically Optimal Robust Low-rank Matrix and Tensor Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Dong Xia, Jian-Feng Cai, Jingyang Li, Yinan Shen","submitted_at":"2022-03-02T09:05:15Z","abstract_excerpt":"Low-rank matrix estimation under heavy-tailed noise is challenging, both computationally and statistically. Convex approaches have been proven statistically optimal but suffer from high computational costs, especially since robust loss functions are usually non-smooth. More recently, computationally fast non-convex approaches via sub-gradient descent are proposed, which, unfortunately, fail to deliver a statistically consistent estimator even under sub-Gaussian noise. In this paper, we introduce a novel Riemannian sub-gradient (RsGrad) algorithm which is not only computationally efficient with"},"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":"2203.00953","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2022-03-02T09:05:15Z","cross_cats_sorted":["cs.IT","math.IT","stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"483fd07522428c8719a125ac645afcd65fcd50dd78923bc5b6766e1eb31b57a2","abstract_canon_sha256":"c51938d04eb99bf778b800610e262258a2de82dd4e6be3c1d5a6e57cb4e86f9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:04.248648Z","signature_b64":"ztSHHm5gxKDnaGTOH3MPeKCFqnJQPI7vff4SU7z2SFTNHQ1WoRp0EuOV/Byqcz893KuhJZsDn8O9TDt4fxVaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20bda2dd7479d0f5de38e0faf3c960a18e8ca01489f1966c51042f7de24a1207","last_reissued_at":"2026-07-05T06:09:04.248213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:04.248213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Computationally Efficient and Statistically Optimal Robust Low-rank Matrix and Tensor Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Dong Xia, Jian-Feng Cai, Jingyang Li, Yinan Shen","submitted_at":"2022-03-02T09:05:15Z","abstract_excerpt":"Low-rank matrix estimation under heavy-tailed noise is challenging, both computationally and statistically. Convex approaches have been proven statistically optimal but suffer from high computational costs, especially since robust loss functions are usually non-smooth. More recently, computationally fast non-convex approaches via sub-gradient descent are proposed, which, unfortunately, fail to deliver a statistically consistent estimator even under sub-Gaussian noise. In this paper, we introduce a novel Riemannian sub-gradient (RsGrad) algorithm which is not only computationally efficient with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00953","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.00953/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":"2203.00953","created_at":"2026-07-05T06:09:04.248267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.00953v4","created_at":"2026-07-05T06:09:04.248267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00953","created_at":"2026-07-05T06:09:04.248267+00:00"},{"alias_kind":"pith_short_12","alias_value":"EC62FXLUPHIP","created_at":"2026-07-05T06:09:04.248267+00:00"},{"alias_kind":"pith_short_16","alias_value":"EC62FXLUPHIPLXRY","created_at":"2026-07-05T06:09:04.248267+00:00"},{"alias_kind":"pith_short_8","alias_value":"EC62FXLU","created_at":"2026-07-05T06:09:04.248267+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/EC62FXLUPHIPLXRY4D5PHSLAUG","json":"https://pith.science/pith/EC62FXLUPHIPLXRY4D5PHSLAUG.json","graph_json":"https://pith.science/api/pith-number/EC62FXLUPHIPLXRY4D5PHSLAUG/graph.json","events_json":"https://pith.science/api/pith-number/EC62FXLUPHIPLXRY4D5PHSLAUG/events.json","paper":"https://pith.science/paper/EC62FXLU"},"agent_actions":{"view_html":"https://pith.science/pith/EC62FXLUPHIPLXRY4D5PHSLAUG","download_json":"https://pith.science/pith/EC62FXLUPHIPLXRY4D5PHSLAUG.json","view_paper":"https://pith.science/paper/EC62FXLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.00953&json=true","fetch_graph":"https://pith.science/api/pith-number/EC62FXLUPHIPLXRY4D5PHSLAUG/graph.json","fetch_events":"https://pith.science/api/pith-number/EC62FXLUPHIPLXRY4D5PHSLAUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EC62FXLUPHIPLXRY4D5PHSLAUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EC62FXLUPHIPLXRY4D5PHSLAUG/action/storage_attestation","attest_author":"https://pith.science/pith/EC62FXLUPHIPLXRY4D5PHSLAUG/action/author_attestation","sign_citation":"https://pith.science/pith/EC62FXLUPHIPLXRY4D5PHSLAUG/action/citation_signature","submit_replication":"https://pith.science/pith/EC62FXLUPHIPLXRY4D5PHSLAUG/action/replication_record"}},"created_at":"2026-07-05T06:09:04.248267+00:00","updated_at":"2026-07-05T06:09:04.248267+00:00"}