{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BFDUNMFABUXVGUCAVKZCIOGDUU","short_pith_number":"pith:BFDUNMFA","schema_version":"1.0","canonical_sha256":"094746b0a00d2f535040aab22438c3a512e63e3f815d7c90bcb4d04f22ec02ec","source":{"kind":"arxiv","id":"1904.10020","version":1},"attestation_state":"computed","paper":{"title":"Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Damek Davis, Dmitriy Drusvyatskiy, Lijun Ding, Mateo D\\'iaz, Vasileios Charisopoulos, Yudong Chen","submitted_at":"2019-04-22T18:36:56Z","abstract_excerpt":"The task of recovering a low-rank matrix from its noisy linear measurements plays a central role in computational science. Smooth formulations of the problem often exhibit an undesirable phenomenon: the condition number, classically defined, scales poorly with the dimension of the ambient space. In contrast, we here show that in a variety of concrete circumstances, nonsmooth penalty formulations do not suffer from the same type of ill-conditioning. Consequently, standard algorithms for nonsmooth optimization, such as subgradient and prox-linear methods, converge at a rapid dimension-independen"},"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":"1904.10020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-04-22T18:36:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6fd80cca9f18de149f2cd77b79d978c3731b67c9ac6f23d4a39bec78f74a82b5","abstract_canon_sha256":"4afdcffdb26131ef1b1a7d18260500277dd73f4a9484d308e68c5da42fa81119"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:55.252668Z","signature_b64":"ZK8qHzXFC2Wrd6GLvVf0A6BZBlKNUIfndsbq/qGYdjUnUW8oMLqfJF+Q3h3iEMElLGeMbfUEE6MhloaXXwVKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"094746b0a00d2f535040aab22438c3a512e63e3f815d7c90bcb4d04f22ec02ec","last_reissued_at":"2026-05-17T23:47:55.252186Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:55.252186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Damek Davis, Dmitriy Drusvyatskiy, Lijun Ding, Mateo D\\'iaz, Vasileios Charisopoulos, Yudong Chen","submitted_at":"2019-04-22T18:36:56Z","abstract_excerpt":"The task of recovering a low-rank matrix from its noisy linear measurements plays a central role in computational science. Smooth formulations of the problem often exhibit an undesirable phenomenon: the condition number, classically defined, scales poorly with the dimension of the ambient space. In contrast, we here show that in a variety of concrete circumstances, nonsmooth penalty formulations do not suffer from the same type of ill-conditioning. Consequently, standard algorithms for nonsmooth optimization, such as subgradient and prox-linear methods, converge at a rapid dimension-independen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.10020","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":"1904.10020","created_at":"2026-05-17T23:47:55.252255+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.10020v1","created_at":"2026-05-17T23:47:55.252255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.10020","created_at":"2026-05-17T23:47:55.252255+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFDUNMFABUXV","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFDUNMFABUXVGUCA","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFDUNMFA","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.09547","citing_title":"Stochastic algorithms with geometric step decay converge linearly on sharp functions","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BFDUNMFABUXVGUCAVKZCIOGDUU","json":"https://pith.science/pith/BFDUNMFABUXVGUCAVKZCIOGDUU.json","graph_json":"https://pith.science/api/pith-number/BFDUNMFABUXVGUCAVKZCIOGDUU/graph.json","events_json":"https://pith.science/api/pith-number/BFDUNMFABUXVGUCAVKZCIOGDUU/events.json","paper":"https://pith.science/paper/BFDUNMFA"},"agent_actions":{"view_html":"https://pith.science/pith/BFDUNMFABUXVGUCAVKZCIOGDUU","download_json":"https://pith.science/pith/BFDUNMFABUXVGUCAVKZCIOGDUU.json","view_paper":"https://pith.science/paper/BFDUNMFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.10020&json=true","fetch_graph":"https://pith.science/api/pith-number/BFDUNMFABUXVGUCAVKZCIOGDUU/graph.json","fetch_events":"https://pith.science/api/pith-number/BFDUNMFABUXVGUCAVKZCIOGDUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFDUNMFABUXVGUCAVKZCIOGDUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFDUNMFABUXVGUCAVKZCIOGDUU/action/storage_attestation","attest_author":"https://pith.science/pith/BFDUNMFABUXVGUCAVKZCIOGDUU/action/author_attestation","sign_citation":"https://pith.science/pith/BFDUNMFABUXVGUCAVKZCIOGDUU/action/citation_signature","submit_replication":"https://pith.science/pith/BFDUNMFABUXVGUCAVKZCIOGDUU/action/replication_record"}},"created_at":"2026-05-17T23:47:55.252255+00:00","updated_at":"2026-05-17T23:47:55.252255+00:00"}