{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:QGH5AJIPIKSC6TNKL5I2DI2W5K","short_pith_number":"pith:QGH5AJIP","schema_version":"1.0","canonical_sha256":"818fd0250f42a42f4daa5f51a1a356ea8797e604f8ded21eb488fe72714a5eb2","source":{"kind":"arxiv","id":"1506.07405","version":3},"attestation_state":"computed","paper":{"title":"Global Convergence of a Grassmannian Gradient Descent Algorithm for Subspace Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.NA","stat.ML"],"primary_cat":"cs.NA","authors_text":"Dejiao Zhang, Laura Balzano","submitted_at":"2015-06-24T14:59:27Z","abstract_excerpt":"It has been observed in a variety of contexts that gradient descent methods have great success in solving low-rank matrix factorization problems, despite the relevant problem formulation being non-convex. We tackle a particular instance of this scenario, where we seek the $d$-dimensional subspace spanned by a streaming data matrix. We apply the natural first order incremental gradient descent method, constraining the gradient method to the Grassmannian. In this paper, we propose an adaptive step size scheme that is greedy for the noiseless case, that maximizes the improvement of our metric of "},"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":"1506.07405","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NA","submitted_at":"2015-06-24T14:59:27Z","cross_cats_sorted":["math.NA","stat.ML"],"title_canon_sha256":"b598ff3c7e77f46142c7961af5abcd7105b458853e92de473c07f3a02fac3ae3","abstract_canon_sha256":"b92525015780d421f9813061b397384eaf10a041dcfb242d61e928023086b442"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:55.131761Z","signature_b64":"oFRIsCrhiyAmyf08wr9QbfgRhTPLIzO/V+U6XgUYDmlvbetITUfrADCo/8obbCNz9uGKncg2zFr4uUNaqlC1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"818fd0250f42a42f4daa5f51a1a356ea8797e604f8ded21eb488fe72714a5eb2","last_reissued_at":"2026-05-18T01:11:55.131389Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:55.131389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global Convergence of a Grassmannian Gradient Descent Algorithm for Subspace Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.NA","stat.ML"],"primary_cat":"cs.NA","authors_text":"Dejiao Zhang, Laura Balzano","submitted_at":"2015-06-24T14:59:27Z","abstract_excerpt":"It has been observed in a variety of contexts that gradient descent methods have great success in solving low-rank matrix factorization problems, despite the relevant problem formulation being non-convex. We tackle a particular instance of this scenario, where we seek the $d$-dimensional subspace spanned by a streaming data matrix. We apply the natural first order incremental gradient descent method, constraining the gradient method to the Grassmannian. In this paper, we propose an adaptive step size scheme that is greedy for the noiseless case, that maximizes the improvement of our metric of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.07405","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":""},"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":"1506.07405","created_at":"2026-05-18T01:11:55.131445+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.07405v3","created_at":"2026-05-18T01:11:55.131445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.07405","created_at":"2026-05-18T01:11:55.131445+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGH5AJIPIKSC","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGH5AJIPIKSC6TNK","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGH5AJIP","created_at":"2026-05-18T12:29:37.295048+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/QGH5AJIPIKSC6TNKL5I2DI2W5K","json":"https://pith.science/pith/QGH5AJIPIKSC6TNKL5I2DI2W5K.json","graph_json":"https://pith.science/api/pith-number/QGH5AJIPIKSC6TNKL5I2DI2W5K/graph.json","events_json":"https://pith.science/api/pith-number/QGH5AJIPIKSC6TNKL5I2DI2W5K/events.json","paper":"https://pith.science/paper/QGH5AJIP"},"agent_actions":{"view_html":"https://pith.science/pith/QGH5AJIPIKSC6TNKL5I2DI2W5K","download_json":"https://pith.science/pith/QGH5AJIPIKSC6TNKL5I2DI2W5K.json","view_paper":"https://pith.science/paper/QGH5AJIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.07405&json=true","fetch_graph":"https://pith.science/api/pith-number/QGH5AJIPIKSC6TNKL5I2DI2W5K/graph.json","fetch_events":"https://pith.science/api/pith-number/QGH5AJIPIKSC6TNKL5I2DI2W5K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGH5AJIPIKSC6TNKL5I2DI2W5K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGH5AJIPIKSC6TNKL5I2DI2W5K/action/storage_attestation","attest_author":"https://pith.science/pith/QGH5AJIPIKSC6TNKL5I2DI2W5K/action/author_attestation","sign_citation":"https://pith.science/pith/QGH5AJIPIKSC6TNKL5I2DI2W5K/action/citation_signature","submit_replication":"https://pith.science/pith/QGH5AJIPIKSC6TNKL5I2DI2W5K/action/replication_record"}},"created_at":"2026-05-18T01:11:55.131445+00:00","updated_at":"2026-05-18T01:11:55.131445+00:00"}