{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VWIQZS6MC7D6NIMZQB6J6XY2OF","short_pith_number":"pith:VWIQZS6M","schema_version":"1.0","canonical_sha256":"ad910ccbcc17c7e6a199807c9f5f1a717dcaa544337c44de68d56a91e9781007","source":{"kind":"arxiv","id":"1805.11454","version":5},"attestation_state":"computed","paper":{"title":"Distributed Stochastic Gradient Tracking Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.SI","stat.ML"],"primary_cat":"math.OC","authors_text":"Angelia Nedi\\'c, Shi Pu","submitted_at":"2018-05-25T23:34:48Z","abstract_excerpt":"In this paper, we study the problem of distributed multi-agent optimization over a network, where each agent possesses a local cost function that is smooth and strongly convex. The global objective is to find a common solution that minimizes the average of all cost functions. Assuming agents only have access to unbiased estimates of the gradients of their local cost functions, we consider a distributed stochastic gradient tracking method (DSGT) and a gossip-like stochastic gradient tracking method (GSGT). We show that, in expectation, the iterates generated by each agent are attracted to a nei"},"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":"1805.11454","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-25T23:34:48Z","cross_cats_sorted":["cs.DC","cs.SI","stat.ML"],"title_canon_sha256":"214693049aa05c35f697d3becc7befd62ff37285f8eba5f412d2868890ce62be","abstract_canon_sha256":"a6a5f7788652b6ccba8e9c53882d811aaec580a3d6a8d3b9a7399d8ba0dd1839"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:46:43.322714Z","signature_b64":"tv/yLH0L4gISr+W5uqBxVGN1DATnJplW51Q7GF3U3H6X+nerLYX2Io9U+kkbrMDU/Y+/yo2A4DsgTrBAhLGvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad910ccbcc17c7e6a199807c9f5f1a717dcaa544337c44de68d56a91e9781007","last_reissued_at":"2026-07-05T00:46:43.322120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:46:43.322120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed Stochastic Gradient Tracking Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.SI","stat.ML"],"primary_cat":"math.OC","authors_text":"Angelia Nedi\\'c, Shi Pu","submitted_at":"2018-05-25T23:34:48Z","abstract_excerpt":"In this paper, we study the problem of distributed multi-agent optimization over a network, where each agent possesses a local cost function that is smooth and strongly convex. The global objective is to find a common solution that minimizes the average of all cost functions. Assuming agents only have access to unbiased estimates of the gradients of their local cost functions, we consider a distributed stochastic gradient tracking method (DSGT) and a gossip-like stochastic gradient tracking method (GSGT). We show that, in expectation, the iterates generated by each agent are attracted to a nei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11454","kind":"arxiv","version":5},"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/1805.11454/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":"1805.11454","created_at":"2026-07-05T00:46:43.322188+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.11454v5","created_at":"2026-07-05T00:46:43.322188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11454","created_at":"2026-07-05T00:46:43.322188+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWIQZS6MC7D6","created_at":"2026-07-05T00:46:43.322188+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWIQZS6MC7D6NIMZ","created_at":"2026-07-05T00:46:43.322188+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWIQZS6M","created_at":"2026-07-05T00:46:43.322188+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.06693","citing_title":"Distributed Stochastic Gradient Method for Non-Convex Problems with Applications in Supervised Learning","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VWIQZS6MC7D6NIMZQB6J6XY2OF","json":"https://pith.science/pith/VWIQZS6MC7D6NIMZQB6J6XY2OF.json","graph_json":"https://pith.science/api/pith-number/VWIQZS6MC7D6NIMZQB6J6XY2OF/graph.json","events_json":"https://pith.science/api/pith-number/VWIQZS6MC7D6NIMZQB6J6XY2OF/events.json","paper":"https://pith.science/paper/VWIQZS6M"},"agent_actions":{"view_html":"https://pith.science/pith/VWIQZS6MC7D6NIMZQB6J6XY2OF","download_json":"https://pith.science/pith/VWIQZS6MC7D6NIMZQB6J6XY2OF.json","view_paper":"https://pith.science/paper/VWIQZS6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.11454&json=true","fetch_graph":"https://pith.science/api/pith-number/VWIQZS6MC7D6NIMZQB6J6XY2OF/graph.json","fetch_events":"https://pith.science/api/pith-number/VWIQZS6MC7D6NIMZQB6J6XY2OF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWIQZS6MC7D6NIMZQB6J6XY2OF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWIQZS6MC7D6NIMZQB6J6XY2OF/action/storage_attestation","attest_author":"https://pith.science/pith/VWIQZS6MC7D6NIMZQB6J6XY2OF/action/author_attestation","sign_citation":"https://pith.science/pith/VWIQZS6MC7D6NIMZQB6J6XY2OF/action/citation_signature","submit_replication":"https://pith.science/pith/VWIQZS6MC7D6NIMZQB6J6XY2OF/action/replication_record"}},"created_at":"2026-07-05T00:46:43.322188+00:00","updated_at":"2026-07-05T00:46:43.322188+00:00"}