{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:RXCA5CCDT3DIYCIYRWWOASSXD4","short_pith_number":"pith:RXCA5CCD","schema_version":"1.0","canonical_sha256":"8dc40e88439ec68c09188dace04a571f345c1e0b97563379de90e826f3d37599","source":{"kind":"arxiv","id":"1710.07205","version":4},"attestation_state":"computed","paper":{"title":"Scalable Robust Matrix Factorization with Nonconvex Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.NA","authors_text":"James T. Kwok, Quanming Yao","submitted_at":"2017-10-19T15:55:27Z","abstract_excerpt":"Robust matrix factorization (RMF), which uses the $\\ell_1$-loss, often outperforms standard matrix factorization using the $\\ell_2$-loss, particularly when outliers are present. The state-of-the-art RMF solver is the RMF-MM algorithm, which, however, cannot utilize data sparsity. Moreover, sometimes even the (convex) $\\ell_1$-loss is not robust enough. In this paper, we propose the use of nonconvex loss to enhance robustness. To address the resultant difficult optimization problem, we use majorization-minimization (MM) optimization and propose a new MM surrogate. To improve scalability, we exp"},"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":"1710.07205","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NA","submitted_at":"2017-10-19T15:55:27Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"99d3ba372781016c4467254081c2fc081566a280ced5d9e1cada684bf8e849d6","abstract_canon_sha256":"8a1f4c33d8c396721a8b6f23cc863dee67393fcb41c9be4afd88b1a076d1a616"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:05.479875Z","signature_b64":"g1m2zSmjkUc0uAlXDMW7UoacDPBFSfvHmZs2XYiHVZFbxJ1o+D0w1gvxtiNaAF0ZGaR6DTvTMh67e54eZ9npDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dc40e88439ec68c09188dace04a571f345c1e0b97563379de90e826f3d37599","last_reissued_at":"2026-05-18T00:05:05.479467Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:05.479467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Robust Matrix Factorization with Nonconvex Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.NA","authors_text":"James T. Kwok, Quanming Yao","submitted_at":"2017-10-19T15:55:27Z","abstract_excerpt":"Robust matrix factorization (RMF), which uses the $\\ell_1$-loss, often outperforms standard matrix factorization using the $\\ell_2$-loss, particularly when outliers are present. The state-of-the-art RMF solver is the RMF-MM algorithm, which, however, cannot utilize data sparsity. Moreover, sometimes even the (convex) $\\ell_1$-loss is not robust enough. In this paper, we propose the use of nonconvex loss to enhance robustness. To address the resultant difficult optimization problem, we use majorization-minimization (MM) optimization and propose a new MM surrogate. To improve scalability, we exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.07205","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":""},"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":"1710.07205","created_at":"2026-05-18T00:05:05.479529+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.07205v4","created_at":"2026-05-18T00:05:05.479529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.07205","created_at":"2026-05-18T00:05:05.479529+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXCA5CCDT3DI","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXCA5CCDT3DIYCIY","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXCA5CCD","created_at":"2026-05-18T12:31:43.269735+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/RXCA5CCDT3DIYCIYRWWOASSXD4","json":"https://pith.science/pith/RXCA5CCDT3DIYCIYRWWOASSXD4.json","graph_json":"https://pith.science/api/pith-number/RXCA5CCDT3DIYCIYRWWOASSXD4/graph.json","events_json":"https://pith.science/api/pith-number/RXCA5CCDT3DIYCIYRWWOASSXD4/events.json","paper":"https://pith.science/paper/RXCA5CCD"},"agent_actions":{"view_html":"https://pith.science/pith/RXCA5CCDT3DIYCIYRWWOASSXD4","download_json":"https://pith.science/pith/RXCA5CCDT3DIYCIYRWWOASSXD4.json","view_paper":"https://pith.science/paper/RXCA5CCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.07205&json=true","fetch_graph":"https://pith.science/api/pith-number/RXCA5CCDT3DIYCIYRWWOASSXD4/graph.json","fetch_events":"https://pith.science/api/pith-number/RXCA5CCDT3DIYCIYRWWOASSXD4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXCA5CCDT3DIYCIYRWWOASSXD4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXCA5CCDT3DIYCIYRWWOASSXD4/action/storage_attestation","attest_author":"https://pith.science/pith/RXCA5CCDT3DIYCIYRWWOASSXD4/action/author_attestation","sign_citation":"https://pith.science/pith/RXCA5CCDT3DIYCIYRWWOASSXD4/action/citation_signature","submit_replication":"https://pith.science/pith/RXCA5CCDT3DIYCIYRWWOASSXD4/action/replication_record"}},"created_at":"2026-05-18T00:05:05.479529+00:00","updated_at":"2026-05-18T00:05:05.479529+00:00"}