{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2LAT42VCU2FHOMQNKER547L7MT","short_pith_number":"pith:2LAT42VC","schema_version":"1.0","canonical_sha256":"d2c13e6aa2a68a77320d5123de7d7f64f0c706ee05fd4d610910aa23d7af66b2","source":{"kind":"arxiv","id":"1709.08114","version":1},"attestation_state":"computed","paper":{"title":"Nonconvex Low-Rank Matrix Recovery with Arbitrary Outliers via Median-Truncated Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT","stat.ML"],"primary_cat":"cs.IT","authors_text":"Huishuai Zhang, Yingbin Liang, Yuanxin Li, Yuejie Chi","submitted_at":"2017-09-23T20:35:12Z","abstract_excerpt":"Recent work has demonstrated the effectiveness of gradient descent for directly recovering the factors of low-rank matrices from random linear measurements in a globally convergent manner when initialized properly. However, the performance of existing algorithms is highly sensitive in the presence of outliers that may take arbitrary values. In this paper, we propose a truncated gradient descent algorithm to improve the robustness against outliers, where the truncation is performed to rule out the contributions of samples that deviate significantly from the {\\em sample median} of measurement re"},"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":"1709.08114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2017-09-23T20:35:12Z","cross_cats_sorted":["math.IT","stat.ML"],"title_canon_sha256":"0828cfffb37438e0df35165132e94858a3cbfb8fc0421afc7633ab459f37f40c","abstract_canon_sha256":"ba0426b930978b1298e373c38c45329e8d90d3d508e522ef3b9513659635d4d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:27.949145Z","signature_b64":"uRTqUMqZlGvdaNvQ1F2BZzcQpfVnfytCWvPnXqw4YLRgQZjS99/DZznoGdAqDffnG415oH3JBp7jaX/5k0qGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2c13e6aa2a68a77320d5123de7d7f64f0c706ee05fd4d610910aa23d7af66b2","last_reissued_at":"2026-05-18T00:34:27.948697Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:27.948697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nonconvex Low-Rank Matrix Recovery with Arbitrary Outliers via Median-Truncated Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT","stat.ML"],"primary_cat":"cs.IT","authors_text":"Huishuai Zhang, Yingbin Liang, Yuanxin Li, Yuejie Chi","submitted_at":"2017-09-23T20:35:12Z","abstract_excerpt":"Recent work has demonstrated the effectiveness of gradient descent for directly recovering the factors of low-rank matrices from random linear measurements in a globally convergent manner when initialized properly. However, the performance of existing algorithms is highly sensitive in the presence of outliers that may take arbitrary values. In this paper, we propose a truncated gradient descent algorithm to improve the robustness against outliers, where the truncation is performed to rule out the contributions of samples that deviate significantly from the {\\em sample median} of measurement re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.08114","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":""},"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":"1709.08114","created_at":"2026-05-18T00:34:27.948763+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.08114v1","created_at":"2026-05-18T00:34:27.948763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.08114","created_at":"2026-05-18T00:34:27.948763+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LAT42VCU2FH","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LAT42VCU2FHOMQN","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LAT42VC","created_at":"2026-05-18T12:30:55.937587+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/2LAT42VCU2FHOMQNKER547L7MT","json":"https://pith.science/pith/2LAT42VCU2FHOMQNKER547L7MT.json","graph_json":"https://pith.science/api/pith-number/2LAT42VCU2FHOMQNKER547L7MT/graph.json","events_json":"https://pith.science/api/pith-number/2LAT42VCU2FHOMQNKER547L7MT/events.json","paper":"https://pith.science/paper/2LAT42VC"},"agent_actions":{"view_html":"https://pith.science/pith/2LAT42VCU2FHOMQNKER547L7MT","download_json":"https://pith.science/pith/2LAT42VCU2FHOMQNKER547L7MT.json","view_paper":"https://pith.science/paper/2LAT42VC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.08114&json=true","fetch_graph":"https://pith.science/api/pith-number/2LAT42VCU2FHOMQNKER547L7MT/graph.json","fetch_events":"https://pith.science/api/pith-number/2LAT42VCU2FHOMQNKER547L7MT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LAT42VCU2FHOMQNKER547L7MT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LAT42VCU2FHOMQNKER547L7MT/action/storage_attestation","attest_author":"https://pith.science/pith/2LAT42VCU2FHOMQNKER547L7MT/action/author_attestation","sign_citation":"https://pith.science/pith/2LAT42VCU2FHOMQNKER547L7MT/action/citation_signature","submit_replication":"https://pith.science/pith/2LAT42VCU2FHOMQNKER547L7MT/action/replication_record"}},"created_at":"2026-05-18T00:34:27.948763+00:00","updated_at":"2026-05-18T00:34:27.948763+00:00"}