{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TVLVJUDC2QJ2K2MOQYWCUW7IUK","short_pith_number":"pith:TVLVJUDC","schema_version":"1.0","canonical_sha256":"9d5754d062d413a5698e862c2a5be8a2ab4ce1347687defb0a6e0e8132a1ac10","source":{"kind":"arxiv","id":"2008.13777","version":2},"attestation_state":"computed","paper":{"title":"Low-rank matrix recovery with non-quadratic loss: projected gradient method and regularity projection oracle","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Lijun Ding, Yudong Chen, Yuqian Zhang","submitted_at":"2020-08-31T17:56:04Z","abstract_excerpt":"Existing results for low-rank matrix recovery largely focus on quadratic loss, which enjoys favorable properties such as restricted strong convexity/smoothness (RSC/RSM) and well conditioning over all low rank matrices. However, many interesting problems involve more general, non-quadratic losses, which do not satisfy such properties. For these problems, standard nonconvex approaches such as rank-constrained projected gradient descent (a.k.a. iterative hard thresholding) and Burer-Monteiro factorization could have poor empirical performance, and there is no satisfactory theory guaranteeing glo"},"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":"2008.13777","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-08-31T17:56:04Z","cross_cats_sorted":["cs.LG","math.OC","math.ST","stat.TH"],"title_canon_sha256":"439baabea95f38be1d484ae9095c0aa17f2843de15e5ca5f5a8e2c50d76ab04a","abstract_canon_sha256":"4236d79e3cac699ce17b03cf324a4ac84f10a851e7cc26bbc196db8268221f22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:53.651403Z","signature_b64":"D/sF2H34dDRLoQ9jndl/8W9KnIRxwuXVHW3cw5Y5xi7O0WG2HXIKeCFdsuWXAQN+EIV7sHvKEJyeuAVpImjtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d5754d062d413a5698e862c2a5be8a2ab4ce1347687defb0a6e0e8132a1ac10","last_reissued_at":"2026-07-05T03:31:53.650826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:53.650826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-rank matrix recovery with non-quadratic loss: projected gradient method and regularity projection oracle","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Lijun Ding, Yudong Chen, Yuqian Zhang","submitted_at":"2020-08-31T17:56:04Z","abstract_excerpt":"Existing results for low-rank matrix recovery largely focus on quadratic loss, which enjoys favorable properties such as restricted strong convexity/smoothness (RSC/RSM) and well conditioning over all low rank matrices. However, many interesting problems involve more general, non-quadratic losses, which do not satisfy such properties. For these problems, standard nonconvex approaches such as rank-constrained projected gradient descent (a.k.a. iterative hard thresholding) and Burer-Monteiro factorization could have poor empirical performance, and there is no satisfactory theory guaranteeing glo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.13777","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/2008.13777/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":"2008.13777","created_at":"2026-07-05T03:31:53.650895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.13777v2","created_at":"2026-07-05T03:31:53.650895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.13777","created_at":"2026-07-05T03:31:53.650895+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVLVJUDC2QJ2","created_at":"2026-07-05T03:31:53.650895+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVLVJUDC2QJ2K2MO","created_at":"2026-07-05T03:31:53.650895+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVLVJUDC","created_at":"2026-07-05T03:31:53.650895+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/TVLVJUDC2QJ2K2MOQYWCUW7IUK","json":"https://pith.science/pith/TVLVJUDC2QJ2K2MOQYWCUW7IUK.json","graph_json":"https://pith.science/api/pith-number/TVLVJUDC2QJ2K2MOQYWCUW7IUK/graph.json","events_json":"https://pith.science/api/pith-number/TVLVJUDC2QJ2K2MOQYWCUW7IUK/events.json","paper":"https://pith.science/paper/TVLVJUDC"},"agent_actions":{"view_html":"https://pith.science/pith/TVLVJUDC2QJ2K2MOQYWCUW7IUK","download_json":"https://pith.science/pith/TVLVJUDC2QJ2K2MOQYWCUW7IUK.json","view_paper":"https://pith.science/paper/TVLVJUDC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.13777&json=true","fetch_graph":"https://pith.science/api/pith-number/TVLVJUDC2QJ2K2MOQYWCUW7IUK/graph.json","fetch_events":"https://pith.science/api/pith-number/TVLVJUDC2QJ2K2MOQYWCUW7IUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVLVJUDC2QJ2K2MOQYWCUW7IUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVLVJUDC2QJ2K2MOQYWCUW7IUK/action/storage_attestation","attest_author":"https://pith.science/pith/TVLVJUDC2QJ2K2MOQYWCUW7IUK/action/author_attestation","sign_citation":"https://pith.science/pith/TVLVJUDC2QJ2K2MOQYWCUW7IUK/action/citation_signature","submit_replication":"https://pith.science/pith/TVLVJUDC2QJ2K2MOQYWCUW7IUK/action/replication_record"}},"created_at":"2026-07-05T03:31:53.650895+00:00","updated_at":"2026-07-05T03:31:53.650895+00:00"}