{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SNYUBF4QCWHUIC7S57J6KAWNTC","short_pith_number":"pith:SNYUBF4Q","schema_version":"1.0","canonical_sha256":"9371409790158f440bf2efd3e502cd98944138cdd354f5dcda46e4c1d01777b5","source":{"kind":"arxiv","id":"2002.10043","version":3},"attestation_state":"computed","paper":{"title":"Complete Dictionary Learning via $\\ell_p$-norm Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","eess.SP","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jun Zhang, Khaled B. Letaief, Vincent Lau, Ye Xue, Yifei Shen","submitted_at":"2020-02-24T02:33:01Z","abstract_excerpt":"Dictionary learning is a classic representation learning method that has been widely applied in signal processing and data analytics. In this paper, we investigate a family of $\\ell_p$-norm ($p>2,p \\in \\mathbb{N}$) maximization approaches for the complete dictionary learning problem from theoretical and algorithmic aspects. Specifically, we prove that the global maximizers of these formulations are very close to the true dictionary with high probability, even when Gaussian noise is present. Based on the generalized power method (GPM), an efficient algorithm is then developed for the $\\ell_p$-b"},"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":"2002.10043","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-24T02:33:01Z","cross_cats_sorted":["cs.IT","eess.SP","math.IT","stat.ML"],"title_canon_sha256":"4f18993136c2df5b23efbdf7d5308a3983e5fac8e72fc3ff84187c53f2491e2b","abstract_canon_sha256":"e50958a1aab76bdf88e81ff637cf195d5f264f7e1461181557445b1905c9ee56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:19:26.193110Z","signature_b64":"M6Z6ovjScPLWZDf5Fe8LiyCGLXcx3dCykrGtV0ylyuBHREhEyZxl8tBCfTj+WZSDfTnFAv4GzmRhNGsuOLZ2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9371409790158f440bf2efd3e502cd98944138cdd354f5dcda46e4c1d01777b5","last_reissued_at":"2026-07-05T01:19:26.192643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:19:26.192643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complete Dictionary Learning via $\\ell_p$-norm Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","eess.SP","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jun Zhang, Khaled B. Letaief, Vincent Lau, Ye Xue, Yifei Shen","submitted_at":"2020-02-24T02:33:01Z","abstract_excerpt":"Dictionary learning is a classic representation learning method that has been widely applied in signal processing and data analytics. In this paper, we investigate a family of $\\ell_p$-norm ($p>2,p \\in \\mathbb{N}$) maximization approaches for the complete dictionary learning problem from theoretical and algorithmic aspects. Specifically, we prove that the global maximizers of these formulations are very close to the true dictionary with high probability, even when Gaussian noise is present. Based on the generalized power method (GPM), an efficient algorithm is then developed for the $\\ell_p$-b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.10043","kind":"arxiv","version":3},"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/2002.10043/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":"2002.10043","created_at":"2026-07-05T01:19:26.192698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.10043v3","created_at":"2026-07-05T01:19:26.192698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.10043","created_at":"2026-07-05T01:19:26.192698+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNYUBF4QCWHU","created_at":"2026-07-05T01:19:26.192698+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNYUBF4QCWHUIC7S","created_at":"2026-07-05T01:19:26.192698+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNYUBF4Q","created_at":"2026-07-05T01:19:26.192698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03801","citing_title":"Fixed Budget vs. Covering Target: The Partial Set Cover Boundary for Bounded VC-Dimension","ref_index":101,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SNYUBF4QCWHUIC7S57J6KAWNTC","json":"https://pith.science/pith/SNYUBF4QCWHUIC7S57J6KAWNTC.json","graph_json":"https://pith.science/api/pith-number/SNYUBF4QCWHUIC7S57J6KAWNTC/graph.json","events_json":"https://pith.science/api/pith-number/SNYUBF4QCWHUIC7S57J6KAWNTC/events.json","paper":"https://pith.science/paper/SNYUBF4Q"},"agent_actions":{"view_html":"https://pith.science/pith/SNYUBF4QCWHUIC7S57J6KAWNTC","download_json":"https://pith.science/pith/SNYUBF4QCWHUIC7S57J6KAWNTC.json","view_paper":"https://pith.science/paper/SNYUBF4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.10043&json=true","fetch_graph":"https://pith.science/api/pith-number/SNYUBF4QCWHUIC7S57J6KAWNTC/graph.json","fetch_events":"https://pith.science/api/pith-number/SNYUBF4QCWHUIC7S57J6KAWNTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNYUBF4QCWHUIC7S57J6KAWNTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNYUBF4QCWHUIC7S57J6KAWNTC/action/storage_attestation","attest_author":"https://pith.science/pith/SNYUBF4QCWHUIC7S57J6KAWNTC/action/author_attestation","sign_citation":"https://pith.science/pith/SNYUBF4QCWHUIC7S57J6KAWNTC/action/citation_signature","submit_replication":"https://pith.science/pith/SNYUBF4QCWHUIC7S57J6KAWNTC/action/replication_record"}},"created_at":"2026-07-05T01:19:26.192698+00:00","updated_at":"2026-07-05T01:19:26.192698+00:00"}