{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5CFZBPTNRJFMEHEBG7LZC3CN3Z","short_pith_number":"pith:5CFZBPTN","schema_version":"1.0","canonical_sha256":"e88b90be6d8a4ac21c8137d7916c4dde5046004891933821a4ac0b38d204cf10","source":{"kind":"arxiv","id":"2303.12277","version":3},"attestation_state":"computed","paper":{"title":"Stochastic Nonsmooth Convex Optimization with Heavy-Tailed Noises: High-Probability Bound, In-Expectation Rate and Initial Distance Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG"],"primary_cat":"math.OC","authors_text":"Zhengyuan Zhou, Zijian Liu","submitted_at":"2023-03-22T03:05:28Z","abstract_excerpt":"Recently, several studies consider the stochastic optimization problem but in a heavy-tailed noise regime, i.e., the difference between the stochastic gradient and the true gradient is assumed to have a finite $p$-th moment (say being upper bounded by $\\sigma^{p}$ for some $\\sigma\\geq0$) where $p\\in(1,2]$, which not only generalizes the traditional finite variance assumption ($p=2$) but also has been observed in practice for several different tasks. Under this challenging assumption, lots of new progress has been made for either convex or nonconvex problems, however, most of which only conside"},"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":"2303.12277","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-03-22T03:05:28Z","cross_cats_sorted":["cs.DS","cs.LG"],"title_canon_sha256":"aaeb3343d8d24521c10975a6a1e62ea6c792a2fa0a14483626c91f17ad75b671","abstract_canon_sha256":"696dac76a8346944e52220b1e62fa5b5c135bf39b018015a0981129494f3877c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:01.195559Z","signature_b64":"xwYT2e3N8Ui2djcWfp/9XZ6inrBdtnDXIYY4xL2ehtLoURMhE5DZfuL/bZ5KFIULuRkPv2dZ2+7bTWqUWKQ7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e88b90be6d8a4ac21c8137d7916c4dde5046004891933821a4ac0b38d204cf10","last_reissued_at":"2026-07-05T06:12:01.195113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:01.195113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Nonsmooth Convex Optimization with Heavy-Tailed Noises: High-Probability Bound, In-Expectation Rate and Initial Distance Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG"],"primary_cat":"math.OC","authors_text":"Zhengyuan Zhou, Zijian Liu","submitted_at":"2023-03-22T03:05:28Z","abstract_excerpt":"Recently, several studies consider the stochastic optimization problem but in a heavy-tailed noise regime, i.e., the difference between the stochastic gradient and the true gradient is assumed to have a finite $p$-th moment (say being upper bounded by $\\sigma^{p}$ for some $\\sigma\\geq0$) where $p\\in(1,2]$, which not only generalizes the traditional finite variance assumption ($p=2$) but also has been observed in practice for several different tasks. Under this challenging assumption, lots of new progress has been made for either convex or nonconvex problems, however, most of which only conside"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12277","kind":"arxiv","version":3},"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/2303.12277/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":"2303.12277","created_at":"2026-07-05T06:12:01.195179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.12277v3","created_at":"2026-07-05T06:12:01.195179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.12277","created_at":"2026-07-05T06:12:01.195179+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CFZBPTNRJFM","created_at":"2026-07-05T06:12:01.195179+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CFZBPTNRJFMEHEB","created_at":"2026-07-05T06:12:01.195179+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CFZBPTN","created_at":"2026-07-05T06:12:01.195179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24879","citing_title":"New Bounds for the Last Iterate of the Stochastic subGradient Method","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18778","citing_title":"Online Distributional Prediction via Latent Cluster Geometry Under Drift and Corruption","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26000","citing_title":"Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00520","citing_title":"In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2501.10258","citing_title":"DADA: Dual Averaging with Distance Adaptation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5CFZBPTNRJFMEHEBG7LZC3CN3Z","json":"https://pith.science/pith/5CFZBPTNRJFMEHEBG7LZC3CN3Z.json","graph_json":"https://pith.science/api/pith-number/5CFZBPTNRJFMEHEBG7LZC3CN3Z/graph.json","events_json":"https://pith.science/api/pith-number/5CFZBPTNRJFMEHEBG7LZC3CN3Z/events.json","paper":"https://pith.science/paper/5CFZBPTN"},"agent_actions":{"view_html":"https://pith.science/pith/5CFZBPTNRJFMEHEBG7LZC3CN3Z","download_json":"https://pith.science/pith/5CFZBPTNRJFMEHEBG7LZC3CN3Z.json","view_paper":"https://pith.science/paper/5CFZBPTN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.12277&json=true","fetch_graph":"https://pith.science/api/pith-number/5CFZBPTNRJFMEHEBG7LZC3CN3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/5CFZBPTNRJFMEHEBG7LZC3CN3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CFZBPTNRJFMEHEBG7LZC3CN3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CFZBPTNRJFMEHEBG7LZC3CN3Z/action/storage_attestation","attest_author":"https://pith.science/pith/5CFZBPTNRJFMEHEBG7LZC3CN3Z/action/author_attestation","sign_citation":"https://pith.science/pith/5CFZBPTNRJFMEHEBG7LZC3CN3Z/action/citation_signature","submit_replication":"https://pith.science/pith/5CFZBPTNRJFMEHEBG7LZC3CN3Z/action/replication_record"}},"created_at":"2026-07-05T06:12:01.195179+00:00","updated_at":"2026-07-05T06:12:01.195179+00:00"}