{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:5WZ4N3WHLWKJSC56P3DGTTZZZP","short_pith_number":"pith:5WZ4N3WH","schema_version":"1.0","canonical_sha256":"edb3c6eec75d94990bbe7ec669cf39cbf21b479ece706a413e1d5d50a76008ed","source":{"kind":"arxiv","id":"1507.08788","version":1},"attestation_state":"computed","paper":{"title":"Fast Stochastic Algorithms for SVD and PCA: Convergence Properties and Convexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ohad Shamir","submitted_at":"2015-07-31T07:57:18Z","abstract_excerpt":"We study the convergence properties of the VR-PCA algorithm introduced by \\cite{shamir2015stochastic} for fast computation of leading singular vectors. We prove several new results, including a formal analysis of a block version of the algorithm, and convergence from random initialization. We also make a few observations of independent interest, such as how pre-initializing with just a single exact power iteration can significantly improve the runtime of stochastic methods, and what are the convexity and non-convexity properties of the underlying optimization problem."},"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":"1507.08788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-31T07:57:18Z","cross_cats_sorted":["cs.NA","math.NA","math.OC","stat.ML"],"title_canon_sha256":"4a9a9e4132c92313c5a54a453cf0f0a643db74e2ffebcdd61edb596af4d07f81","abstract_canon_sha256":"32ea8bacda57234bb5e2f49ca187aca3c563a24e2ce90b8e7ea12462c668588b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:02.845887Z","signature_b64":"k9F0ajcCDkgAVz5xhP2GdGlnNTIdbPp7tML/avP9WqM28y0XL/WszW0bGErsqrdjIcWao8vyzpiTueKter1bBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edb3c6eec75d94990bbe7ec669cf39cbf21b479ece706a413e1d5d50a76008ed","last_reissued_at":"2026-05-18T01:36:02.845311Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:02.845311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Stochastic Algorithms for SVD and PCA: Convergence Properties and Convexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ohad Shamir","submitted_at":"2015-07-31T07:57:18Z","abstract_excerpt":"We study the convergence properties of the VR-PCA algorithm introduced by \\cite{shamir2015stochastic} for fast computation of leading singular vectors. We prove several new results, including a formal analysis of a block version of the algorithm, and convergence from random initialization. We also make a few observations of independent interest, such as how pre-initializing with just a single exact power iteration can significantly improve the runtime of stochastic methods, and what are the convexity and non-convexity properties of the underlying optimization problem."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.08788","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":"1507.08788","created_at":"2026-05-18T01:36:02.845411+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.08788v1","created_at":"2026-05-18T01:36:02.845411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.08788","created_at":"2026-05-18T01:36:02.845411+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WZ4N3WHLWKJ","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WZ4N3WHLWKJSC56","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WZ4N3WH","created_at":"2026-05-18T12:29:07.941421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.27942","citing_title":"Quantum principal component analysis without eigenvector recovery","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WZ4N3WHLWKJSC56P3DGTTZZZP","json":"https://pith.science/pith/5WZ4N3WHLWKJSC56P3DGTTZZZP.json","graph_json":"https://pith.science/api/pith-number/5WZ4N3WHLWKJSC56P3DGTTZZZP/graph.json","events_json":"https://pith.science/api/pith-number/5WZ4N3WHLWKJSC56P3DGTTZZZP/events.json","paper":"https://pith.science/paper/5WZ4N3WH"},"agent_actions":{"view_html":"https://pith.science/pith/5WZ4N3WHLWKJSC56P3DGTTZZZP","download_json":"https://pith.science/pith/5WZ4N3WHLWKJSC56P3DGTTZZZP.json","view_paper":"https://pith.science/paper/5WZ4N3WH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.08788&json=true","fetch_graph":"https://pith.science/api/pith-number/5WZ4N3WHLWKJSC56P3DGTTZZZP/graph.json","fetch_events":"https://pith.science/api/pith-number/5WZ4N3WHLWKJSC56P3DGTTZZZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WZ4N3WHLWKJSC56P3DGTTZZZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WZ4N3WHLWKJSC56P3DGTTZZZP/action/storage_attestation","attest_author":"https://pith.science/pith/5WZ4N3WHLWKJSC56P3DGTTZZZP/action/author_attestation","sign_citation":"https://pith.science/pith/5WZ4N3WHLWKJSC56P3DGTTZZZP/action/citation_signature","submit_replication":"https://pith.science/pith/5WZ4N3WHLWKJSC56P3DGTTZZZP/action/replication_record"}},"created_at":"2026-05-18T01:36:02.845411+00:00","updated_at":"2026-05-18T01:36:02.845411+00:00"}