{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:NZLQAWNXUXZTEMBQGPOYWGX4RN","short_pith_number":"pith:NZLQAWNX","schema_version":"1.0","canonical_sha256":"6e570059b7a5f332303033dd8b1afc8b7314677ac4c91455d21fcfa0d45128d4","source":{"kind":"arxiv","id":"1603.03516","version":2},"attestation_state":"computed","paper":{"title":"An $\\ell_{\\infty}$ Eigenvector Perturbation Bound and Its Application to Robust Covariance Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.NA","stat.TH"],"primary_cat":"math.ST","authors_text":"Jianqing Fan, Weichen Wang, Yiqiao Zhong","submitted_at":"2016-03-11T04:39:33Z","abstract_excerpt":"In statistics and machine learning, people are often interested in the eigenvectors (or singular vectors) of certain matrices (e.g. covariance matrices, data matrices, etc). However, those matrices are usually perturbed by noises or statistical errors, either from random sampling or structural patterns. One usually employs Davis-Kahan $\\sin \\theta$ theorem to bound the difference between the eigenvectors of a matrix $A$ and those of a perturbed matrix $\\widetilde{A} = A + E$, in terms of $\\ell_2$ norm. In this paper, we prove that when $A$ is a low-rank and incoherent matrix, the $\\ell_{\\infty"},"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":"1603.03516","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2016-03-11T04:39:33Z","cross_cats_sorted":["math.NA","stat.TH"],"title_canon_sha256":"48dd890cd95f90361852aa757226ccc5e55d7ddfc5570d5307f7cb568a9ffef9","abstract_canon_sha256":"78e28030f2c32109c61ee6116aa285383269b72332319381a95831738b157e8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:13.435489Z","signature_b64":"QawVdsHHAlnA5AXKnZriAJCUhgqYN9McdNfOOPGIuo1JJsVwm8exuT4QkLzZyJ38MADSKel9/jeHVjcJHvTQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e570059b7a5f332303033dd8b1afc8b7314677ac4c91455d21fcfa0d45128d4","last_reissued_at":"2026-05-18T00:43:13.434886Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:13.434886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An $\\ell_{\\infty}$ Eigenvector Perturbation Bound and Its Application to Robust Covariance Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.NA","stat.TH"],"primary_cat":"math.ST","authors_text":"Jianqing Fan, Weichen Wang, Yiqiao Zhong","submitted_at":"2016-03-11T04:39:33Z","abstract_excerpt":"In statistics and machine learning, people are often interested in the eigenvectors (or singular vectors) of certain matrices (e.g. covariance matrices, data matrices, etc). However, those matrices are usually perturbed by noises or statistical errors, either from random sampling or structural patterns. One usually employs Davis-Kahan $\\sin \\theta$ theorem to bound the difference between the eigenvectors of a matrix $A$ and those of a perturbed matrix $\\widetilde{A} = A + E$, in terms of $\\ell_2$ norm. In this paper, we prove that when $A$ is a low-rank and incoherent matrix, the $\\ell_{\\infty"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.03516","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":""},"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":"1603.03516","created_at":"2026-05-18T00:43:13.434968+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.03516v2","created_at":"2026-05-18T00:43:13.434968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.03516","created_at":"2026-05-18T00:43:13.434968+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZLQAWNXUXZT","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZLQAWNXUXZTEMBQ","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZLQAWNX","created_at":"2026-05-18T12:30:36.002864+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/NZLQAWNXUXZTEMBQGPOYWGX4RN","json":"https://pith.science/pith/NZLQAWNXUXZTEMBQGPOYWGX4RN.json","graph_json":"https://pith.science/api/pith-number/NZLQAWNXUXZTEMBQGPOYWGX4RN/graph.json","events_json":"https://pith.science/api/pith-number/NZLQAWNXUXZTEMBQGPOYWGX4RN/events.json","paper":"https://pith.science/paper/NZLQAWNX"},"agent_actions":{"view_html":"https://pith.science/pith/NZLQAWNXUXZTEMBQGPOYWGX4RN","download_json":"https://pith.science/pith/NZLQAWNXUXZTEMBQGPOYWGX4RN.json","view_paper":"https://pith.science/paper/NZLQAWNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.03516&json=true","fetch_graph":"https://pith.science/api/pith-number/NZLQAWNXUXZTEMBQGPOYWGX4RN/graph.json","fetch_events":"https://pith.science/api/pith-number/NZLQAWNXUXZTEMBQGPOYWGX4RN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZLQAWNXUXZTEMBQGPOYWGX4RN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZLQAWNXUXZTEMBQGPOYWGX4RN/action/storage_attestation","attest_author":"https://pith.science/pith/NZLQAWNXUXZTEMBQGPOYWGX4RN/action/author_attestation","sign_citation":"https://pith.science/pith/NZLQAWNXUXZTEMBQGPOYWGX4RN/action/citation_signature","submit_replication":"https://pith.science/pith/NZLQAWNXUXZTEMBQGPOYWGX4RN/action/replication_record"}},"created_at":"2026-05-18T00:43:13.434968+00:00","updated_at":"2026-05-18T00:43:13.434968+00:00"}