{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6DNBSWNTVRIPMG5MSA26MD5LXA","short_pith_number":"pith:6DNBSWNT","schema_version":"1.0","canonical_sha256":"f0da1959b3ac50f61bac9035e60fabb807ac9e2d291b6e344752bb87f23d25d2","source":{"kind":"arxiv","id":"2008.04195","version":2},"attestation_state":"computed","paper":{"title":"An improved convergence analysis for decentralized online stochastic non-convex optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA","cs.SY","eess.SY","stat.ML"],"primary_cat":"math.OC","authors_text":"Ran Xin, Soummya Kar, Usman A. Khan","submitted_at":"2020-08-10T15:29:13Z","abstract_excerpt":"In this paper, we study decentralized online stochastic non-convex optimization over a network of nodes. Integrating a technique called gradient tracking in decentralized stochastic gradient descent, we show that the resulting algorithm, GT-DSGD, enjoys certain desirable characteristics towards minimizing a sum of smooth non-convex functions. In particular, for general smooth non-convex functions, we establish non-asymptotic characterizations of GT-DSGD and derive the conditions under which it achieves network-independent performances that match the centralized minibatch SGD. In contrast, the "},"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":"2008.04195","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-08-10T15:29:13Z","cross_cats_sorted":["cs.LG","cs.MA","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"15eb53f36b87133de067e8992a905f4f6601e46138dd5eed06915c83b832e5db","abstract_canon_sha256":"d012b8e77982a00aff017dab51a03e77b4744371b5c38cbe271db97b0d4be955"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:19.604238Z","signature_b64":"be2f/8O47DOKPCi5xzV//xceeXzEOtpT6RQtl4WXhHrTBuxBNCOArrW9JRluSOiWeOgIdfkg/etKkLlel4L9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0da1959b3ac50f61bac9035e60fabb807ac9e2d291b6e344752bb87f23d25d2","last_reissued_at":"2026-07-05T02:33:19.603816Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:19.603816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An improved convergence analysis for decentralized online stochastic non-convex optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA","cs.SY","eess.SY","stat.ML"],"primary_cat":"math.OC","authors_text":"Ran Xin, Soummya Kar, Usman A. Khan","submitted_at":"2020-08-10T15:29:13Z","abstract_excerpt":"In this paper, we study decentralized online stochastic non-convex optimization over a network of nodes. Integrating a technique called gradient tracking in decentralized stochastic gradient descent, we show that the resulting algorithm, GT-DSGD, enjoys certain desirable characteristics towards minimizing a sum of smooth non-convex functions. In particular, for general smooth non-convex functions, we establish non-asymptotic characterizations of GT-DSGD and derive the conditions under which it achieves network-independent performances that match the centralized minibatch SGD. In contrast, the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.04195","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/2008.04195/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":"2008.04195","created_at":"2026-07-05T02:33:19.603884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.04195v2","created_at":"2026-07-05T02:33:19.603884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.04195","created_at":"2026-07-05T02:33:19.603884+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DNBSWNTVRIP","created_at":"2026-07-05T02:33:19.603884+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DNBSWNTVRIPMG5M","created_at":"2026-07-05T02:33:19.603884+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DNBSWNT","created_at":"2026-07-05T02:33:19.603884+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.02712","citing_title":"Decentralized Stochastic Gradient Tracking for Non-convex Empirical Risk Minimization","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DNBSWNTVRIPMG5MSA26MD5LXA","json":"https://pith.science/pith/6DNBSWNTVRIPMG5MSA26MD5LXA.json","graph_json":"https://pith.science/api/pith-number/6DNBSWNTVRIPMG5MSA26MD5LXA/graph.json","events_json":"https://pith.science/api/pith-number/6DNBSWNTVRIPMG5MSA26MD5LXA/events.json","paper":"https://pith.science/paper/6DNBSWNT"},"agent_actions":{"view_html":"https://pith.science/pith/6DNBSWNTVRIPMG5MSA26MD5LXA","download_json":"https://pith.science/pith/6DNBSWNTVRIPMG5MSA26MD5LXA.json","view_paper":"https://pith.science/paper/6DNBSWNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.04195&json=true","fetch_graph":"https://pith.science/api/pith-number/6DNBSWNTVRIPMG5MSA26MD5LXA/graph.json","fetch_events":"https://pith.science/api/pith-number/6DNBSWNTVRIPMG5MSA26MD5LXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DNBSWNTVRIPMG5MSA26MD5LXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DNBSWNTVRIPMG5MSA26MD5LXA/action/storage_attestation","attest_author":"https://pith.science/pith/6DNBSWNTVRIPMG5MSA26MD5LXA/action/author_attestation","sign_citation":"https://pith.science/pith/6DNBSWNTVRIPMG5MSA26MD5LXA/action/citation_signature","submit_replication":"https://pith.science/pith/6DNBSWNTVRIPMG5MSA26MD5LXA/action/replication_record"}},"created_at":"2026-07-05T02:33:19.603884+00:00","updated_at":"2026-07-05T02:33:19.603884+00:00"}