{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MQP5XD4KBAAXLKRNSXU3TDOJVB","short_pith_number":"pith:MQP5XD4K","schema_version":"1.0","canonical_sha256":"641fdb8f8a080175aa2d95e9b98dc9a859bb2426c4cf8c3d5d84a13f6594ddfa","source":{"kind":"arxiv","id":"2310.01860","version":2},"attestation_state":"computed","paper":{"title":"High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Abdurakhmon Sadiev, Alexander Gasnikov, Eduard Gorbunov, Gauthier Gidel, Marina Danilova, Pavel Dvurechensky, Peter Richt\\'arik, Samuel Horv\\'ath","submitted_at":"2023-10-03T07:49:17Z","abstract_excerpt":"High-probability analysis of stochastic first-order optimization methods under mild assumptions on the noise has been gaining a lot of attention in recent years. Typically, gradient clipping is one of the key algorithmic ingredients to derive good high-probability guarantees when the noise is heavy-tailed. However, if implemented na\\\"ively, clipping can spoil the convergence of the popular methods for composite and distributed optimization (Prox-SGD/Parallel SGD) even in the absence of any noise. Due to this reason, many works on high-probability analysis consider only unconstrained non-distri"},"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":"2310.01860","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-10-03T07:49:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"38e09e240da12e18d3c8750bd39504f9b58af604cf01ea71666c59dfd844aa49","abstract_canon_sha256":"37e9f4622e3c5da3c79c98def833f36fca4fc8cd0ee88814f0c5ee629672d3bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:47.551846Z","signature_b64":"6fTO1fbJvFQ8Y8ZDVWGnTPzocvVYA+evykwV2K5C4iQIQk3PxPZyKHyHnD+ayrNZqN4OFyLa6ODxH2SVJc1eCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"641fdb8f8a080175aa2d95e9b98dc9a859bb2426c4cf8c3d5d84a13f6594ddfa","last_reissued_at":"2026-07-05T08:47:47.551396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:47.551396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Abdurakhmon Sadiev, Alexander Gasnikov, Eduard Gorbunov, Gauthier Gidel, Marina Danilova, Pavel Dvurechensky, Peter Richt\\'arik, Samuel Horv\\'ath","submitted_at":"2023-10-03T07:49:17Z","abstract_excerpt":"High-probability analysis of stochastic first-order optimization methods under mild assumptions on the noise has been gaining a lot of attention in recent years. Typically, gradient clipping is one of the key algorithmic ingredients to derive good high-probability guarantees when the noise is heavy-tailed. However, if implemented na\\\"ively, clipping can spoil the convergence of the popular methods for composite and distributed optimization (Prox-SGD/Parallel SGD) even in the absence of any noise. Due to this reason, many works on high-probability analysis consider only unconstrained non-distri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01860","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/2310.01860/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":"2310.01860","created_at":"2026-07-05T08:47:47.551451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01860v2","created_at":"2026-07-05T08:47:47.551451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01860","created_at":"2026-07-05T08:47:47.551451+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQP5XD4KBAAX","created_at":"2026-07-05T08:47:47.551451+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQP5XD4KBAAXLKRN","created_at":"2026-07-05T08:47:47.551451+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQP5XD4K","created_at":"2026-07-05T08:47:47.551451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15388","citing_title":"Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQP5XD4KBAAXLKRNSXU3TDOJVB","json":"https://pith.science/pith/MQP5XD4KBAAXLKRNSXU3TDOJVB.json","graph_json":"https://pith.science/api/pith-number/MQP5XD4KBAAXLKRNSXU3TDOJVB/graph.json","events_json":"https://pith.science/api/pith-number/MQP5XD4KBAAXLKRNSXU3TDOJVB/events.json","paper":"https://pith.science/paper/MQP5XD4K"},"agent_actions":{"view_html":"https://pith.science/pith/MQP5XD4KBAAXLKRNSXU3TDOJVB","download_json":"https://pith.science/pith/MQP5XD4KBAAXLKRNSXU3TDOJVB.json","view_paper":"https://pith.science/paper/MQP5XD4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01860&json=true","fetch_graph":"https://pith.science/api/pith-number/MQP5XD4KBAAXLKRNSXU3TDOJVB/graph.json","fetch_events":"https://pith.science/api/pith-number/MQP5XD4KBAAXLKRNSXU3TDOJVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQP5XD4KBAAXLKRNSXU3TDOJVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQP5XD4KBAAXLKRNSXU3TDOJVB/action/storage_attestation","attest_author":"https://pith.science/pith/MQP5XD4KBAAXLKRNSXU3TDOJVB/action/author_attestation","sign_citation":"https://pith.science/pith/MQP5XD4KBAAXLKRNSXU3TDOJVB/action/citation_signature","submit_replication":"https://pith.science/pith/MQP5XD4KBAAXLKRNSXU3TDOJVB/action/replication_record"}},"created_at":"2026-07-05T08:47:47.551451+00:00","updated_at":"2026-07-05T08:47:47.551451+00:00"}