{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QFCGWGGBQXF64QUIUZLEHU3AJO","short_pith_number":"pith:QFCGWGGB","schema_version":"1.0","canonical_sha256":"81446b18c185cbee4288a65643d3604bbbb92935d7f1b687268b4d853b403475","source":{"kind":"arxiv","id":"1809.10313","version":1},"attestation_state":"computed","paper":{"title":"Efficient Dictionary Learning with Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Dar Gilboa, John Wright, Sam Buchanan","submitted_at":"2018-09-27T02:14:40Z","abstract_excerpt":"Randomly initialized first-order optimization algorithms are the method of choice for solving many high-dimensional nonconvex problems in machine learning, yet general theoretical guarantees cannot rule out convergence to critical points of poor objective value. For some highly structured nonconvex problems however, the success of gradient descent can be understood by studying the geometry of the objective. We study one such problem -- complete orthogonal dictionary learning, and provide converge guarantees for randomly initialized gradient descent to the neighborhood of a global optimum. The "},"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":"1809.10313","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-27T02:14:40Z","cross_cats_sorted":[],"title_canon_sha256":"cbe3a34d4d4bdf656f76bc5104189570aafe4cb786477fa03ee3fd46b095dfbf","abstract_canon_sha256":"33f494aa554f23d9d1b2b97263b508fe4c0c3745b95b65806650e5295cfebd85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:38.616542Z","signature_b64":"2vsftq79pARBoOZoyW+mMM7yNNi5nuITlLz6GSAtEyDZPxaFKe46mkynugIshzQxfc9vTn2igvvnFRLktEduCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81446b18c185cbee4288a65643d3604bbbb92935d7f1b687268b4d853b403475","last_reissued_at":"2026-05-18T00:04:38.616066Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:38.616066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Dictionary Learning with Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Dar Gilboa, John Wright, Sam Buchanan","submitted_at":"2018-09-27T02:14:40Z","abstract_excerpt":"Randomly initialized first-order optimization algorithms are the method of choice for solving many high-dimensional nonconvex problems in machine learning, yet general theoretical guarantees cannot rule out convergence to critical points of poor objective value. For some highly structured nonconvex problems however, the success of gradient descent can be understood by studying the geometry of the objective. We study one such problem -- complete orthogonal dictionary learning, and provide converge guarantees for randomly initialized gradient descent to the neighborhood of a global optimum. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.10313","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":"1809.10313","created_at":"2026-05-18T00:04:38.616131+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.10313v1","created_at":"2026-05-18T00:04:38.616131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.10313","created_at":"2026-05-18T00:04:38.616131+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFCGWGGBQXF6","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFCGWGGBQXF64QUI","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFCGWGGB","created_at":"2026-05-18T12:32:46.962924+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/QFCGWGGBQXF64QUIUZLEHU3AJO","json":"https://pith.science/pith/QFCGWGGBQXF64QUIUZLEHU3AJO.json","graph_json":"https://pith.science/api/pith-number/QFCGWGGBQXF64QUIUZLEHU3AJO/graph.json","events_json":"https://pith.science/api/pith-number/QFCGWGGBQXF64QUIUZLEHU3AJO/events.json","paper":"https://pith.science/paper/QFCGWGGB"},"agent_actions":{"view_html":"https://pith.science/pith/QFCGWGGBQXF64QUIUZLEHU3AJO","download_json":"https://pith.science/pith/QFCGWGGBQXF64QUIUZLEHU3AJO.json","view_paper":"https://pith.science/paper/QFCGWGGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.10313&json=true","fetch_graph":"https://pith.science/api/pith-number/QFCGWGGBQXF64QUIUZLEHU3AJO/graph.json","fetch_events":"https://pith.science/api/pith-number/QFCGWGGBQXF64QUIUZLEHU3AJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFCGWGGBQXF64QUIUZLEHU3AJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFCGWGGBQXF64QUIUZLEHU3AJO/action/storage_attestation","attest_author":"https://pith.science/pith/QFCGWGGBQXF64QUIUZLEHU3AJO/action/author_attestation","sign_citation":"https://pith.science/pith/QFCGWGGBQXF64QUIUZLEHU3AJO/action/citation_signature","submit_replication":"https://pith.science/pith/QFCGWGGBQXF64QUIUZLEHU3AJO/action/replication_record"}},"created_at":"2026-05-18T00:04:38.616131+00:00","updated_at":"2026-05-18T00:04:38.616131+00:00"}