{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GQ6S56IBE7VKTYIZ5S6KHHFMW2","short_pith_number":"pith:GQ6S56IB","schema_version":"1.0","canonical_sha256":"343d2ef90127eaa9e119ecbca39cacb697f583709db1e32761ece3abeab92e1c","source":{"kind":"arxiv","id":"1808.09645","version":1},"attestation_state":"computed","paper":{"title":"Diffusion Approximations for Online Principal Component Estimation and Global Convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chris Junchi Li, Han Liu, Mengdi Wang, Tong Zhang","submitted_at":"2018-08-29T05:36:07Z","abstract_excerpt":"In this paper, we propose to adopt the diffusion approximation tools to study the dynamics of Oja's iteration which is an online stochastic gradient descent method for the principal component analysis. Oja's iteration maintains a running estimate of the true principal component from streaming data and enjoys less temporal and spatial complexities. We show that the Oja's iteration for the top eigenvector generates a continuous-state discrete-time Markov chain over the unit sphere. We characterize the Oja's iteration in three phases using diffusion approximation and weak convergence tools. Our t"},"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":"1808.09645","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-08-29T05:36:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0ee4053449747c5843b5604da1938733a17416af97fdda4839cb20e4d5003136","abstract_canon_sha256":"c08e65d28809fb06fffdf1ad6f39ff88f481ef430ee71c307b841f5a70afd1f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:54.912284Z","signature_b64":"n9MQKCbxJFHDye/eVIRoFQhC+XoXfIzVbXvirs8juppvFYut134lYNJEM56UsG83DOQgHX3Tf/sXhv4BsxJhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"343d2ef90127eaa9e119ecbca39cacb697f583709db1e32761ece3abeab92e1c","last_reissued_at":"2026-05-18T00:06:54.911705Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:54.911705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Approximations for Online Principal Component Estimation and Global Convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chris Junchi Li, Han Liu, Mengdi Wang, Tong Zhang","submitted_at":"2018-08-29T05:36:07Z","abstract_excerpt":"In this paper, we propose to adopt the diffusion approximation tools to study the dynamics of Oja's iteration which is an online stochastic gradient descent method for the principal component analysis. Oja's iteration maintains a running estimate of the true principal component from streaming data and enjoys less temporal and spatial complexities. We show that the Oja's iteration for the top eigenvector generates a continuous-state discrete-time Markov chain over the unit sphere. We characterize the Oja's iteration in three phases using diffusion approximation and weak convergence tools. Our t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09645","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":"1808.09645","created_at":"2026-05-18T00:06:54.911792+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.09645v1","created_at":"2026-05-18T00:06:54.911792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09645","created_at":"2026-05-18T00:06:54.911792+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQ6S56IBE7VK","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQ6S56IBE7VKTYIZ","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQ6S56IB","created_at":"2026-05-18T12:32:25.280505+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/GQ6S56IBE7VKTYIZ5S6KHHFMW2","json":"https://pith.science/pith/GQ6S56IBE7VKTYIZ5S6KHHFMW2.json","graph_json":"https://pith.science/api/pith-number/GQ6S56IBE7VKTYIZ5S6KHHFMW2/graph.json","events_json":"https://pith.science/api/pith-number/GQ6S56IBE7VKTYIZ5S6KHHFMW2/events.json","paper":"https://pith.science/paper/GQ6S56IB"},"agent_actions":{"view_html":"https://pith.science/pith/GQ6S56IBE7VKTYIZ5S6KHHFMW2","download_json":"https://pith.science/pith/GQ6S56IBE7VKTYIZ5S6KHHFMW2.json","view_paper":"https://pith.science/paper/GQ6S56IB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.09645&json=true","fetch_graph":"https://pith.science/api/pith-number/GQ6S56IBE7VKTYIZ5S6KHHFMW2/graph.json","fetch_events":"https://pith.science/api/pith-number/GQ6S56IBE7VKTYIZ5S6KHHFMW2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQ6S56IBE7VKTYIZ5S6KHHFMW2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQ6S56IBE7VKTYIZ5S6KHHFMW2/action/storage_attestation","attest_author":"https://pith.science/pith/GQ6S56IBE7VKTYIZ5S6KHHFMW2/action/author_attestation","sign_citation":"https://pith.science/pith/GQ6S56IBE7VKTYIZ5S6KHHFMW2/action/citation_signature","submit_replication":"https://pith.science/pith/GQ6S56IBE7VKTYIZ5S6KHHFMW2/action/replication_record"}},"created_at":"2026-05-18T00:06:54.911792+00:00","updated_at":"2026-05-18T00:06:54.911792+00:00"}