{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UZCOCY4MQFNS7IZAARUECBCU6X","short_pith_number":"pith:UZCOCY4M","schema_version":"1.0","canonical_sha256":"a644e1638c815b2fa3200468410454f5ce038b77bfab0b3958a443dd0e1992af","source":{"kind":"arxiv","id":"1802.06967","version":2},"attestation_state":"computed","paper":{"title":"Recovery of simultaneous low rank and two-way sparse coefficient matrices, a nonconvex approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Ming Yu, Mladen Kolar, Varun Gupta","submitted_at":"2018-02-20T04:52:26Z","abstract_excerpt":"We study the problem of recovery of matrices that are simultaneously low rank and row and/or column sparse. Such matrices appear in recent applications in cognitive neuroscience, imaging, computer vision, macroeconomics, and genetics. We propose a GDT (Gradient Descent with hard Thresholding) algorithm to efficiently recover matrices with such structure, by minimizing a bi-convex function over a nonconvex set of constraints. We show linear convergence of the iterates obtained by GDT to a region within statistical error of an optimal solution. As an application of our method, we consider multi-"},"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":"1802.06967","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-20T04:52:26Z","cross_cats_sorted":[],"title_canon_sha256":"7943613d35ad64a32e26d478520fc88ce3727c0c4a19a4da351f8165697f48a9","abstract_canon_sha256":"378933b189ad476bac1c2c0af91e1476ba7b6944d6b48ea6af2c4d8c488ef9b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:55.674484Z","signature_b64":"JMwNBiLryL2z05u36RxPh+bzdple0VI10BDHoq7cKHh+ettPSMsgSqtvlJB/b07FTIzasgpTEup0ezOcInpKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a644e1638c815b2fa3200468410454f5ce038b77bfab0b3958a443dd0e1992af","last_reissued_at":"2026-05-17T23:48:55.673749Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:55.673749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recovery of simultaneous low rank and two-way sparse coefficient matrices, a nonconvex approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Ming Yu, Mladen Kolar, Varun Gupta","submitted_at":"2018-02-20T04:52:26Z","abstract_excerpt":"We study the problem of recovery of matrices that are simultaneously low rank and row and/or column sparse. Such matrices appear in recent applications in cognitive neuroscience, imaging, computer vision, macroeconomics, and genetics. We propose a GDT (Gradient Descent with hard Thresholding) algorithm to efficiently recover matrices with such structure, by minimizing a bi-convex function over a nonconvex set of constraints. We show linear convergence of the iterates obtained by GDT to a region within statistical error of an optimal solution. As an application of our method, we consider multi-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06967","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":"1802.06967","created_at":"2026-05-17T23:48:55.673853+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.06967v2","created_at":"2026-05-17T23:48:55.673853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06967","created_at":"2026-05-17T23:48:55.673853+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZCOCY4MQFNS","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZCOCY4MQFNS7IZA","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZCOCY4M","created_at":"2026-05-18T12:32:56.356000+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/UZCOCY4MQFNS7IZAARUECBCU6X","json":"https://pith.science/pith/UZCOCY4MQFNS7IZAARUECBCU6X.json","graph_json":"https://pith.science/api/pith-number/UZCOCY4MQFNS7IZAARUECBCU6X/graph.json","events_json":"https://pith.science/api/pith-number/UZCOCY4MQFNS7IZAARUECBCU6X/events.json","paper":"https://pith.science/paper/UZCOCY4M"},"agent_actions":{"view_html":"https://pith.science/pith/UZCOCY4MQFNS7IZAARUECBCU6X","download_json":"https://pith.science/pith/UZCOCY4MQFNS7IZAARUECBCU6X.json","view_paper":"https://pith.science/paper/UZCOCY4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.06967&json=true","fetch_graph":"https://pith.science/api/pith-number/UZCOCY4MQFNS7IZAARUECBCU6X/graph.json","fetch_events":"https://pith.science/api/pith-number/UZCOCY4MQFNS7IZAARUECBCU6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZCOCY4MQFNS7IZAARUECBCU6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZCOCY4MQFNS7IZAARUECBCU6X/action/storage_attestation","attest_author":"https://pith.science/pith/UZCOCY4MQFNS7IZAARUECBCU6X/action/author_attestation","sign_citation":"https://pith.science/pith/UZCOCY4MQFNS7IZAARUECBCU6X/action/citation_signature","submit_replication":"https://pith.science/pith/UZCOCY4MQFNS7IZAARUECBCU6X/action/replication_record"}},"created_at":"2026-05-17T23:48:55.673853+00:00","updated_at":"2026-05-17T23:48:55.673853+00:00"}