{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QXXUHJJ2Q2UEEEEFPRIDQK3XT6","short_pith_number":"pith:QXXUHJJ2","schema_version":"1.0","canonical_sha256":"85ef43a53a86a84210857c50382b779fb1895bab5fae9ffdaddfc5bb6a2c754e","source":{"kind":"arxiv","id":"2112.10389","version":2},"attestation_state":"computed","paper":{"title":"Decentralized Stochastic Proximal Gradient Descent with Variance Reduction over Time-varying Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NI","math.OC"],"primary_cat":"cs.LG","authors_text":"Jessie Hui Wang, John C.S. Lui, Xin Wang, Xuanjie Li, Yuedong Xu","submitted_at":"2021-12-20T08:23:36Z","abstract_excerpt":"In decentralized learning, a network of nodes cooperate to minimize an overall objective function that is usually the finite-sum of their local objectives, and incorporates a non-smooth regularization term for the better generalization ability. Decentralized stochastic proximal gradient (DSPG) method is commonly used to train this type of learning models, while the convergence rate is retarded by the variance of stochastic gradients. In this paper, we propose a novel algorithm, namely DPSVRG, to accelerate the decentralized training by leveraging the variance reduction technique. The basic ide"},"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":"2112.10389","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-20T08:23:36Z","cross_cats_sorted":["cs.NI","math.OC"],"title_canon_sha256":"01cadf3edfee87b4ea9329742acc70ba994d3e424bd0dfc381aa2fd160d120e0","abstract_canon_sha256":"3419bed2e1fafb0b4ebc7409e77573adfe1b53394af059ebe2fcbcc33c089cdf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:53.219631Z","signature_b64":"rk5nboIutiBdhhO8OThJYN9V4I3qDxlAdLZtIBM4qsCpTKixvlf4wrspKFgjpOUSrZ5m0SrbO/ZKHRRo7HMOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85ef43a53a86a84210857c50382b779fb1895bab5fae9ffdaddfc5bb6a2c754e","last_reissued_at":"2026-07-05T03:50:53.219154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:53.219154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Stochastic Proximal Gradient Descent with Variance Reduction over Time-varying Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NI","math.OC"],"primary_cat":"cs.LG","authors_text":"Jessie Hui Wang, John C.S. Lui, Xin Wang, Xuanjie Li, Yuedong Xu","submitted_at":"2021-12-20T08:23:36Z","abstract_excerpt":"In decentralized learning, a network of nodes cooperate to minimize an overall objective function that is usually the finite-sum of their local objectives, and incorporates a non-smooth regularization term for the better generalization ability. Decentralized stochastic proximal gradient (DSPG) method is commonly used to train this type of learning models, while the convergence rate is retarded by the variance of stochastic gradients. In this paper, we propose a novel algorithm, namely DPSVRG, to accelerate the decentralized training by leveraging the variance reduction technique. The basic ide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10389","kind":"arxiv","version":2},"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/2112.10389/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":"2112.10389","created_at":"2026-07-05T03:50:53.219210+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.10389v2","created_at":"2026-07-05T03:50:53.219210+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10389","created_at":"2026-07-05T03:50:53.219210+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXXUHJJ2Q2UE","created_at":"2026-07-05T03:50:53.219210+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXXUHJJ2Q2UEEEEF","created_at":"2026-07-05T03:50:53.219210+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXXUHJJ2","created_at":"2026-07-05T03:50:53.219210+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/QXXUHJJ2Q2UEEEEFPRIDQK3XT6","json":"https://pith.science/pith/QXXUHJJ2Q2UEEEEFPRIDQK3XT6.json","graph_json":"https://pith.science/api/pith-number/QXXUHJJ2Q2UEEEEFPRIDQK3XT6/graph.json","events_json":"https://pith.science/api/pith-number/QXXUHJJ2Q2UEEEEFPRIDQK3XT6/events.json","paper":"https://pith.science/paper/QXXUHJJ2"},"agent_actions":{"view_html":"https://pith.science/pith/QXXUHJJ2Q2UEEEEFPRIDQK3XT6","download_json":"https://pith.science/pith/QXXUHJJ2Q2UEEEEFPRIDQK3XT6.json","view_paper":"https://pith.science/paper/QXXUHJJ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.10389&json=true","fetch_graph":"https://pith.science/api/pith-number/QXXUHJJ2Q2UEEEEFPRIDQK3XT6/graph.json","fetch_events":"https://pith.science/api/pith-number/QXXUHJJ2Q2UEEEEFPRIDQK3XT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXXUHJJ2Q2UEEEEFPRIDQK3XT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXXUHJJ2Q2UEEEEFPRIDQK3XT6/action/storage_attestation","attest_author":"https://pith.science/pith/QXXUHJJ2Q2UEEEEFPRIDQK3XT6/action/author_attestation","sign_citation":"https://pith.science/pith/QXXUHJJ2Q2UEEEEFPRIDQK3XT6/action/citation_signature","submit_replication":"https://pith.science/pith/QXXUHJJ2Q2UEEEEFPRIDQK3XT6/action/replication_record"}},"created_at":"2026-07-05T03:50:53.219210+00:00","updated_at":"2026-07-05T03:50:53.219210+00:00"}