{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2ASBVTSVHGO32LH5RI64VNI4OI","short_pith_number":"pith:2ASBVTSV","schema_version":"1.0","canonical_sha256":"d0241ace55399dbd2cfd8a3dcab51c72276696ff2b28b2af00b5377578422303","source":{"kind":"arxiv","id":"2506.11647","version":2},"attestation_state":"computed","paper":{"title":"High Probability Convergence of Distributed Clipped Stochastic Gradient Descent with Heavy-tailed Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Kaihong Lu, Long Wang, Yuchen Yang","submitted_at":"2025-06-13T10:22:22Z","abstract_excerpt":"In this paper, the problem of distributed optimization is studied via a network of agents. Each agent only has access to a noisy gradient of its own objective function, and can communicate with its neighbors via a network. To handle this problem, a distributed clipped stochastic gradient descent algorithm is proposed, and the high probability convergence of the algorithm is studied. Existing works on distributed algorithms involving stochastic gradients only consider the light-tailed noises. Different from them, we study the case with heavy-tailed settings. Under mild assumptions on the graph "},"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":"2506.11647","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-13T10:22:22Z","cross_cats_sorted":[],"title_canon_sha256":"94d14bd1fc0339c019c748be60267e33cf0f48d1ebbd3a27e6e3394e7554b139","abstract_canon_sha256":"fc28b889dc3788f7650b0dd70ffa0ada3dc94026e4da6e83b5db3720e3f41185"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:29.971187Z","signature_b64":"bxf/p+7B804yX2TP80aIBbM+Wr12F376yX3AE0f9pV8Wz8NauZKWaVinPXpWeswVvO6uyLCfxwQCDZoxJ2NSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0241ace55399dbd2cfd8a3dcab51c72276696ff2b28b2af00b5377578422303","last_reissued_at":"2026-07-05T11:23:29.970705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:29.970705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High Probability Convergence of Distributed Clipped Stochastic Gradient Descent with Heavy-tailed Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Kaihong Lu, Long Wang, Yuchen Yang","submitted_at":"2025-06-13T10:22:22Z","abstract_excerpt":"In this paper, the problem of distributed optimization is studied via a network of agents. Each agent only has access to a noisy gradient of its own objective function, and can communicate with its neighbors via a network. To handle this problem, a distributed clipped stochastic gradient descent algorithm is proposed, and the high probability convergence of the algorithm is studied. Existing works on distributed algorithms involving stochastic gradients only consider the light-tailed noises. Different from them, we study the case with heavy-tailed settings. Under mild assumptions on the graph "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11647","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/2506.11647/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":"2506.11647","created_at":"2026-07-05T11:23:29.970759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11647v2","created_at":"2026-07-05T11:23:29.970759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11647","created_at":"2026-07-05T11:23:29.970759+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ASBVTSVHGO3","created_at":"2026-07-05T11:23:29.970759+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ASBVTSVHGO32LH5","created_at":"2026-07-05T11:23:29.970759+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ASBVTSV","created_at":"2026-07-05T11:23:29.970759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.06141","citing_title":"High-Probability Convergence Guarantees of Decentralized SGD","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2510.06141","citing_title":"High-Probability Convergence Guarantees of Decentralized SGD","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ASBVTSVHGO32LH5RI64VNI4OI","json":"https://pith.science/pith/2ASBVTSVHGO32LH5RI64VNI4OI.json","graph_json":"https://pith.science/api/pith-number/2ASBVTSVHGO32LH5RI64VNI4OI/graph.json","events_json":"https://pith.science/api/pith-number/2ASBVTSVHGO32LH5RI64VNI4OI/events.json","paper":"https://pith.science/paper/2ASBVTSV"},"agent_actions":{"view_html":"https://pith.science/pith/2ASBVTSVHGO32LH5RI64VNI4OI","download_json":"https://pith.science/pith/2ASBVTSVHGO32LH5RI64VNI4OI.json","view_paper":"https://pith.science/paper/2ASBVTSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11647&json=true","fetch_graph":"https://pith.science/api/pith-number/2ASBVTSVHGO32LH5RI64VNI4OI/graph.json","fetch_events":"https://pith.science/api/pith-number/2ASBVTSVHGO32LH5RI64VNI4OI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ASBVTSVHGO32LH5RI64VNI4OI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ASBVTSVHGO32LH5RI64VNI4OI/action/storage_attestation","attest_author":"https://pith.science/pith/2ASBVTSVHGO32LH5RI64VNI4OI/action/author_attestation","sign_citation":"https://pith.science/pith/2ASBVTSVHGO32LH5RI64VNI4OI/action/citation_signature","submit_replication":"https://pith.science/pith/2ASBVTSVHGO32LH5RI64VNI4OI/action/replication_record"}},"created_at":"2026-07-05T11:23:29.970759+00:00","updated_at":"2026-07-05T11:23:29.970759+00:00"}