{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B3AWM4PVX55LD3IQS4XOTRGF47","short_pith_number":"pith:B3AWM4PV","schema_version":"1.0","canonical_sha256":"0ec16671f5bf7ab1ed10972ee9c4c5e7c22fe24556d0a8564a6b1e39628cef71","source":{"kind":"arxiv","id":"2302.05437","version":2},"attestation_state":"computed","paper":{"title":"High Probability Convergence of Clipped-SGD Under Heavy-tailed Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Alina Ene, Huy Le Nguyen, Ta Duy Nguyen, Thien Hang Nguyen","submitted_at":"2023-02-10T18:54:51Z","abstract_excerpt":"While the convergence behaviors of stochastic gradient methods are well understood \\emph{in expectation}, there still exist many gaps in the understanding of their convergence with \\emph{high probability}, where the convergence rate has a logarithmic dependency on the desired success probability parameter. In the \\emph{heavy-tailed noise} setting, where the stochastic gradient noise only has bounded $p$-th moments for some $p\\in(1,2]$, existing works could only show bounds \\emph{in expectation} for a variant of stochastic gradient descent (SGD) with clipped gradients, or high probability bound"},"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":"2302.05437","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-02-10T18:54:51Z","cross_cats_sorted":[],"title_canon_sha256":"818da2f6b6b7cb739561ed370da3290294d823bad084743e6e504e9d4ab8fd70","abstract_canon_sha256":"4a71ef840f82dee1ecec0494326652b3af87b6f82ea265d067390373ba0483bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:16.099296Z","signature_b64":"xwLcF19fq5YERjIcFPaQozGEQ03iOsXHaPZ7Cg51MgKVq+LN8p5gHMheFjR8hciPFPgd1B1r/hzKeqvw801eBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ec16671f5bf7ab1ed10972ee9c4c5e7c22fe24556d0a8564a6b1e39628cef71","last_reissued_at":"2026-07-05T05:57:16.098795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:16.098795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High Probability Convergence of Clipped-SGD Under Heavy-tailed Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Alina Ene, Huy Le Nguyen, Ta Duy Nguyen, Thien Hang Nguyen","submitted_at":"2023-02-10T18:54:51Z","abstract_excerpt":"While the convergence behaviors of stochastic gradient methods are well understood \\emph{in expectation}, there still exist many gaps in the understanding of their convergence with \\emph{high probability}, where the convergence rate has a logarithmic dependency on the desired success probability parameter. In the \\emph{heavy-tailed noise} setting, where the stochastic gradient noise only has bounded $p$-th moments for some $p\\in(1,2]$, existing works could only show bounds \\emph{in expectation} for a variant of stochastic gradient descent (SGD) with clipped gradients, or high probability bound"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05437","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/2302.05437/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":"2302.05437","created_at":"2026-07-05T05:57:16.098856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.05437v2","created_at":"2026-07-05T05:57:16.098856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05437","created_at":"2026-07-05T05:57:16.098856+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3AWM4PVX55L","created_at":"2026-07-05T05:57:16.098856+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3AWM4PVX55LD3IQ","created_at":"2026-07-05T05:57:16.098856+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3AWM4PV","created_at":"2026-07-05T05:57:16.098856+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02701","citing_title":"Robust and Fast Training via Per-Sample Clipping","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24513","citing_title":"Zeroth-Order Nonconvex Nonsmooth Optimization with Heavy-Tailed Noise","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07634","citing_title":"Robust stochastic first order methods in heavy-tailed noise via medoid mini-batch gradient sampling","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B3AWM4PVX55LD3IQS4XOTRGF47","json":"https://pith.science/pith/B3AWM4PVX55LD3IQS4XOTRGF47.json","graph_json":"https://pith.science/api/pith-number/B3AWM4PVX55LD3IQS4XOTRGF47/graph.json","events_json":"https://pith.science/api/pith-number/B3AWM4PVX55LD3IQS4XOTRGF47/events.json","paper":"https://pith.science/paper/B3AWM4PV"},"agent_actions":{"view_html":"https://pith.science/pith/B3AWM4PVX55LD3IQS4XOTRGF47","download_json":"https://pith.science/pith/B3AWM4PVX55LD3IQS4XOTRGF47.json","view_paper":"https://pith.science/paper/B3AWM4PV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.05437&json=true","fetch_graph":"https://pith.science/api/pith-number/B3AWM4PVX55LD3IQS4XOTRGF47/graph.json","fetch_events":"https://pith.science/api/pith-number/B3AWM4PVX55LD3IQS4XOTRGF47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3AWM4PVX55LD3IQS4XOTRGF47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3AWM4PVX55LD3IQS4XOTRGF47/action/storage_attestation","attest_author":"https://pith.science/pith/B3AWM4PVX55LD3IQS4XOTRGF47/action/author_attestation","sign_citation":"https://pith.science/pith/B3AWM4PVX55LD3IQS4XOTRGF47/action/citation_signature","submit_replication":"https://pith.science/pith/B3AWM4PVX55LD3IQS4XOTRGF47/action/replication_record"}},"created_at":"2026-07-05T05:57:16.098856+00:00","updated_at":"2026-07-05T05:57:16.098856+00:00"}