{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QPCJXNDFAGRT33CDQC5QKHLAPN","short_pith_number":"pith:QPCJXNDF","schema_version":"1.0","canonical_sha256":"83c49bb46501a33dec4380bb051d607b45b30d5c4ad68f25b788d0b2354abb3c","source":{"kind":"arxiv","id":"2208.13643","version":1},"attestation_state":"computed","paper":{"title":"A Variance-Reduced Stochastic Gradient Tracking Algorithm for Decentralized Optimization with Orthogonality Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY","stat.ML"],"primary_cat":"math.OC","authors_text":"Lei Wang, Xin Liu","submitted_at":"2022-08-29T14:46:44Z","abstract_excerpt":"Decentralized optimization with orthogonality constraints is found widely in scientific computing and data science. Since the orthogonality constraints are nonconvex, it is quite challenging to design efficient algorithms. Existing approaches leverage the geometric tools from Riemannian optimization to solve this problem at the cost of high sample and communication complexities. To relieve this difficulty, based on two novel techniques that can waive the orthogonality constraints, we propose a variance-reduced stochastic gradient tracking (VRSGT) algorithm with the convergence rate of $O(1 / k"},"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":"2208.13643","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-08-29T14:46:44Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"7b6e199e17e682ad8d4b9af8e5b45be790612444edb323a1233a3172d2dc96f0","abstract_canon_sha256":"0d0edc07b2f65c3e9fe309cb9528f432178b09a284531510b4ca24ed8320a948"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:44.552972Z","signature_b64":"x9rZVYX/dfflw95NLEEavf1o6wCmZLeeMk5qc9H0VdESDGxVksPGeMJYENmJxKQWJk18t8yVATLMnSm3mQAyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83c49bb46501a33dec4380bb051d607b45b30d5c4ad68f25b788d0b2354abb3c","last_reissued_at":"2026-07-05T07:30:44.552476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:44.552476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Variance-Reduced Stochastic Gradient Tracking Algorithm for Decentralized Optimization with Orthogonality Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY","stat.ML"],"primary_cat":"math.OC","authors_text":"Lei Wang, Xin Liu","submitted_at":"2022-08-29T14:46:44Z","abstract_excerpt":"Decentralized optimization with orthogonality constraints is found widely in scientific computing and data science. Since the orthogonality constraints are nonconvex, it is quite challenging to design efficient algorithms. Existing approaches leverage the geometric tools from Riemannian optimization to solve this problem at the cost of high sample and communication complexities. To relieve this difficulty, based on two novel techniques that can waive the orthogonality constraints, we propose a variance-reduced stochastic gradient tracking (VRSGT) algorithm with the convergence rate of $O(1 / k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.13643","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/2208.13643/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":"2208.13643","created_at":"2026-07-05T07:30:44.552540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.13643v1","created_at":"2026-07-05T07:30:44.552540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.13643","created_at":"2026-07-05T07:30:44.552540+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPCJXNDFAGRT","created_at":"2026-07-05T07:30:44.552540+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPCJXNDFAGRT33CD","created_at":"2026-07-05T07:30:44.552540+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPCJXNDF","created_at":"2026-07-05T07:30:44.552540+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/QPCJXNDFAGRT33CDQC5QKHLAPN","json":"https://pith.science/pith/QPCJXNDFAGRT33CDQC5QKHLAPN.json","graph_json":"https://pith.science/api/pith-number/QPCJXNDFAGRT33CDQC5QKHLAPN/graph.json","events_json":"https://pith.science/api/pith-number/QPCJXNDFAGRT33CDQC5QKHLAPN/events.json","paper":"https://pith.science/paper/QPCJXNDF"},"agent_actions":{"view_html":"https://pith.science/pith/QPCJXNDFAGRT33CDQC5QKHLAPN","download_json":"https://pith.science/pith/QPCJXNDFAGRT33CDQC5QKHLAPN.json","view_paper":"https://pith.science/paper/QPCJXNDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.13643&json=true","fetch_graph":"https://pith.science/api/pith-number/QPCJXNDFAGRT33CDQC5QKHLAPN/graph.json","fetch_events":"https://pith.science/api/pith-number/QPCJXNDFAGRT33CDQC5QKHLAPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPCJXNDFAGRT33CDQC5QKHLAPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPCJXNDFAGRT33CDQC5QKHLAPN/action/storage_attestation","attest_author":"https://pith.science/pith/QPCJXNDFAGRT33CDQC5QKHLAPN/action/author_attestation","sign_citation":"https://pith.science/pith/QPCJXNDFAGRT33CDQC5QKHLAPN/action/citation_signature","submit_replication":"https://pith.science/pith/QPCJXNDFAGRT33CDQC5QKHLAPN/action/replication_record"}},"created_at":"2026-07-05T07:30:44.552540+00:00","updated_at":"2026-07-05T07:30:44.552540+00:00"}