{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BXVATFRLKX6JP65JECV67U45VO","short_pith_number":"pith:BXVATFRL","schema_version":"1.0","canonical_sha256":"0dea09962b55fc97fba920abefd39daba11c334b914e1a35f5b1912de7ec9efa","source":{"kind":"arxiv","id":"2207.04600","version":2},"attestation_state":"computed","paper":{"title":"Optimal Clustering by Lloyd Algorithm for Low-Rank Mixture Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","stat.ME","stat.TH"],"primary_cat":"math.ST","authors_text":"Dong Xia, Zhongyuan Lyu","submitted_at":"2022-07-11T03:16:10Z","abstract_excerpt":"This paper investigates the computational and statistical limits in clustering matrix-valued observations. We propose a low-rank mixture model (LrMM), adapted from the classical Gaussian mixture model (GMM) to treat matrix-valued observations, which assumes low-rankness for population center matrices. A computationally efficient clustering method is designed by integrating Lloyd's algorithm and low-rank approximation. Once well-initialized, the algorithm converges fast and achieves an exponential-type clustering error rate that is minimax optimal. Meanwhile, we show that a tensor-based spectra"},"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":"2207.04600","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2022-07-11T03:16:10Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","stat.ME","stat.TH"],"title_canon_sha256":"c6b4319fb3547ee7c22f4d4ba6d5161cbcaedabd911e3331f6f450b6d55d3b7d","abstract_canon_sha256":"d79bc056cc49e4bc846bd1f5ac31af87a458ccbb010e026d0764d9e9f6149fe9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:17.130242Z","signature_b64":"2rXNHA0ZCdsIxuvnT0WBb7u3hs7AR05vmw+w3lKb2wTv2u8gQQZ3/7iy2DCJW577hBtdEvdD/1jIhKvalN3gCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dea09962b55fc97fba920abefd39daba11c334b914e1a35f5b1912de7ec9efa","last_reissued_at":"2026-07-05T06:18:17.129833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:17.129833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Clustering by Lloyd Algorithm for Low-Rank Mixture Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","stat.ME","stat.TH"],"primary_cat":"math.ST","authors_text":"Dong Xia, Zhongyuan Lyu","submitted_at":"2022-07-11T03:16:10Z","abstract_excerpt":"This paper investigates the computational and statistical limits in clustering matrix-valued observations. We propose a low-rank mixture model (LrMM), adapted from the classical Gaussian mixture model (GMM) to treat matrix-valued observations, which assumes low-rankness for population center matrices. A computationally efficient clustering method is designed by integrating Lloyd's algorithm and low-rank approximation. Once well-initialized, the algorithm converges fast and achieves an exponential-type clustering error rate that is minimax optimal. Meanwhile, we show that a tensor-based spectra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04600","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/2207.04600/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":"2207.04600","created_at":"2026-07-05T06:18:17.129890+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.04600v2","created_at":"2026-07-05T06:18:17.129890+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04600","created_at":"2026-07-05T06:18:17.129890+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXVATFRLKX6J","created_at":"2026-07-05T06:18:17.129890+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXVATFRLKX6JP65J","created_at":"2026-07-05T06:18:17.129890+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXVATFRL","created_at":"2026-07-05T06:18:17.129890+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10748","citing_title":"Computational Complexity of Statistics: New Insights from Low-Degree Polynomials","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BXVATFRLKX6JP65JECV67U45VO","json":"https://pith.science/pith/BXVATFRLKX6JP65JECV67U45VO.json","graph_json":"https://pith.science/api/pith-number/BXVATFRLKX6JP65JECV67U45VO/graph.json","events_json":"https://pith.science/api/pith-number/BXVATFRLKX6JP65JECV67U45VO/events.json","paper":"https://pith.science/paper/BXVATFRL"},"agent_actions":{"view_html":"https://pith.science/pith/BXVATFRLKX6JP65JECV67U45VO","download_json":"https://pith.science/pith/BXVATFRLKX6JP65JECV67U45VO.json","view_paper":"https://pith.science/paper/BXVATFRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.04600&json=true","fetch_graph":"https://pith.science/api/pith-number/BXVATFRLKX6JP65JECV67U45VO/graph.json","fetch_events":"https://pith.science/api/pith-number/BXVATFRLKX6JP65JECV67U45VO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXVATFRLKX6JP65JECV67U45VO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXVATFRLKX6JP65JECV67U45VO/action/storage_attestation","attest_author":"https://pith.science/pith/BXVATFRLKX6JP65JECV67U45VO/action/author_attestation","sign_citation":"https://pith.science/pith/BXVATFRLKX6JP65JECV67U45VO/action/citation_signature","submit_replication":"https://pith.science/pith/BXVATFRLKX6JP65JECV67U45VO/action/replication_record"}},"created_at":"2026-07-05T06:18:17.129890+00:00","updated_at":"2026-07-05T06:18:17.129890+00:00"}