{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2MJQKJ7GVOGLATPYE5QHS3GVDG","short_pith_number":"pith:2MJQKJ7G","schema_version":"1.0","canonical_sha256":"d3130527e6ab8cb04df82760796cd5199eb5652eaf0470ba0b39183f2b7b077c","source":{"kind":"arxiv","id":"2102.03646","version":1},"attestation_state":"computed","paper":{"title":"Streaming k-PCA: Efficient guarantees for Oja's algorithm, beyond rank-one updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"cs.DS","authors_text":"De Huang, Jonathan Niles-Weed, Rachel Ward","submitted_at":"2021-02-06T19:21:24Z","abstract_excerpt":"We analyze Oja's algorithm for streaming $k$-PCA and prove that it achieves performance nearly matching that of an optimal offline algorithm. Given access to a sequence of i.i.d. $d \\times d$ symmetric matrices, we show that Oja's algorithm can obtain an accurate approximation to the subspace of the top $k$ eigenvectors of their expectation using a number of samples that scales polylogarithmically with $d$. Previously, such a result was only known in the case where the updates have rank one. Our analysis is based on recently developed matrix concentration tools, which allow us to prove strong "},"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":"2102.03646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2021-02-06T19:21:24Z","cross_cats_sorted":["cs.LG","math.PR"],"title_canon_sha256":"0a4a20c2845f9e11ecd249e395fb8e6b32ea2de07b245a6a4f7acc583c3e1e9d","abstract_canon_sha256":"d1dbeeab6f1d2c1cded959f0fe1b25238c2c39405bc7d4a9e9d1e3582256a154"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:25.784263Z","signature_b64":"k3KRLa26ohTgD+umNTtoDYWObEGomaQmIfLR4sRObbSrt4iW0AZ3BPIqmkMvqx5XzfzDCH2VRccOVCAz9il1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3130527e6ab8cb04df82760796cd5199eb5652eaf0470ba0b39183f2b7b077c","last_reissued_at":"2026-07-05T02:13:25.783865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:25.783865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming k-PCA: Efficient guarantees for Oja's algorithm, beyond rank-one updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"cs.DS","authors_text":"De Huang, Jonathan Niles-Weed, Rachel Ward","submitted_at":"2021-02-06T19:21:24Z","abstract_excerpt":"We analyze Oja's algorithm for streaming $k$-PCA and prove that it achieves performance nearly matching that of an optimal offline algorithm. Given access to a sequence of i.i.d. $d \\times d$ symmetric matrices, we show that Oja's algorithm can obtain an accurate approximation to the subspace of the top $k$ eigenvectors of their expectation using a number of samples that scales polylogarithmically with $d$. Previously, such a result was only known in the case where the updates have rank one. Our analysis is based on recently developed matrix concentration tools, which allow us to prove strong "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.03646","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2102.03646/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":"2102.03646","created_at":"2026-07-05T02:13:25.783929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.03646v1","created_at":"2026-07-05T02:13:25.783929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.03646","created_at":"2026-07-05T02:13:25.783929+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MJQKJ7GVOGL","created_at":"2026-07-05T02:13:25.783929+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MJQKJ7GVOGLATPY","created_at":"2026-07-05T02:13:25.783929+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MJQKJ7G","created_at":"2026-07-05T02:13:25.783929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12655","citing_title":"Beyond Sin-Squared Error: Linear-Time Entrywise Uncertainty Quantification for Streaming PCA","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2MJQKJ7GVOGLATPYE5QHS3GVDG","json":"https://pith.science/pith/2MJQKJ7GVOGLATPYE5QHS3GVDG.json","graph_json":"https://pith.science/api/pith-number/2MJQKJ7GVOGLATPYE5QHS3GVDG/graph.json","events_json":"https://pith.science/api/pith-number/2MJQKJ7GVOGLATPYE5QHS3GVDG/events.json","paper":"https://pith.science/paper/2MJQKJ7G"},"agent_actions":{"view_html":"https://pith.science/pith/2MJQKJ7GVOGLATPYE5QHS3GVDG","download_json":"https://pith.science/pith/2MJQKJ7GVOGLATPYE5QHS3GVDG.json","view_paper":"https://pith.science/paper/2MJQKJ7G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.03646&json=true","fetch_graph":"https://pith.science/api/pith-number/2MJQKJ7GVOGLATPYE5QHS3GVDG/graph.json","fetch_events":"https://pith.science/api/pith-number/2MJQKJ7GVOGLATPYE5QHS3GVDG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MJQKJ7GVOGLATPYE5QHS3GVDG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MJQKJ7GVOGLATPYE5QHS3GVDG/action/storage_attestation","attest_author":"https://pith.science/pith/2MJQKJ7GVOGLATPYE5QHS3GVDG/action/author_attestation","sign_citation":"https://pith.science/pith/2MJQKJ7GVOGLATPYE5QHS3GVDG/action/citation_signature","submit_replication":"https://pith.science/pith/2MJQKJ7GVOGLATPYE5QHS3GVDG/action/replication_record"}},"created_at":"2026-07-05T02:13:25.783929+00:00","updated_at":"2026-07-05T02:13:25.783929+00:00"}