{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HRBC2HBKDYH2FV5GKMSEZMREME","short_pith_number":"pith:HRBC2HBK","schema_version":"1.0","canonical_sha256":"3c422d1c2a1e0fa2d7a653244cb2246111ccbc8654b139960efae19a886c5f91","source":{"kind":"arxiv","id":"2310.18784","version":7},"attestation_state":"computed","paper":{"title":"High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Aleksandar Armacki, Dragana Bajovic, Dusan Jakovetic, Gauri Joshi, Pranay Sharma, Soummya Kar","submitted_at":"2023-10-28T18:53:41Z","abstract_excerpt":"We study high-probability convergence guarantees of learning on streaming data in the presence of heavy-tailed noise. In the proposed scenario, the model is updated in an online fashion, as new information is observed, without storing any additional data. To combat the heavy-tailed noise, we consider a general framework of nonlinear stochastic gradient descent (SGD), providing several strong results. First, for non-convex costs and component-wise nonlinearities, we establish a convergence rate arbitrarily close to $\\mathcal{O}\\left(t^{-\\frac{1}{4}}\\right)$, whose exponent is independent of noi"},"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":"2310.18784","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-28T18:53:41Z","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"f675822d539980b1f9e693c44dd1c412c1b6a84f605ab27e5af9544fe6b78f89","abstract_canon_sha256":"590214d8e50752d48dc828d9ee396f8675246e963c1f23f0df11324df2f54d3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:01.987619Z","signature_b64":"23B407xeScmnQj8Prlt1jfWu/LhjKCNzQ90loqVpMl8cnLIwAzYCQ3lzFljGFeY9ZirKkgZkOOQT/ETegKTCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c422d1c2a1e0fa2d7a653244cb2246111ccbc8654b139960efae19a886c5f91","last_reissued_at":"2026-07-05T08:14:01.987173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:01.987173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Aleksandar Armacki, Dragana Bajovic, Dusan Jakovetic, Gauri Joshi, Pranay Sharma, Soummya Kar","submitted_at":"2023-10-28T18:53:41Z","abstract_excerpt":"We study high-probability convergence guarantees of learning on streaming data in the presence of heavy-tailed noise. In the proposed scenario, the model is updated in an online fashion, as new information is observed, without storing any additional data. To combat the heavy-tailed noise, we consider a general framework of nonlinear stochastic gradient descent (SGD), providing several strong results. First, for non-convex costs and component-wise nonlinearities, we establish a convergence rate arbitrarily close to $\\mathcal{O}\\left(t^{-\\frac{1}{4}}\\right)$, whose exponent is independent of noi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18784","kind":"arxiv","version":7},"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/2310.18784/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":"2310.18784","created_at":"2026-07-05T08:14:01.987221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18784v7","created_at":"2026-07-05T08:14:01.987221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18784","created_at":"2026-07-05T08:14:01.987221+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRBC2HBKDYH2","created_at":"2026-07-05T08:14:01.987221+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRBC2HBKDYH2FV5G","created_at":"2026-07-05T08:14:01.987221+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRBC2HBK","created_at":"2026-07-05T08:14:01.987221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HRBC2HBKDYH2FV5GKMSEZMREME","json":"https://pith.science/pith/HRBC2HBKDYH2FV5GKMSEZMREME.json","graph_json":"https://pith.science/api/pith-number/HRBC2HBKDYH2FV5GKMSEZMREME/graph.json","events_json":"https://pith.science/api/pith-number/HRBC2HBKDYH2FV5GKMSEZMREME/events.json","paper":"https://pith.science/paper/HRBC2HBK"},"agent_actions":{"view_html":"https://pith.science/pith/HRBC2HBKDYH2FV5GKMSEZMREME","download_json":"https://pith.science/pith/HRBC2HBKDYH2FV5GKMSEZMREME.json","view_paper":"https://pith.science/paper/HRBC2HBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18784&json=true","fetch_graph":"https://pith.science/api/pith-number/HRBC2HBKDYH2FV5GKMSEZMREME/graph.json","fetch_events":"https://pith.science/api/pith-number/HRBC2HBKDYH2FV5GKMSEZMREME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRBC2HBKDYH2FV5GKMSEZMREME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRBC2HBKDYH2FV5GKMSEZMREME/action/storage_attestation","attest_author":"https://pith.science/pith/HRBC2HBKDYH2FV5GKMSEZMREME/action/author_attestation","sign_citation":"https://pith.science/pith/HRBC2HBKDYH2FV5GKMSEZMREME/action/citation_signature","submit_replication":"https://pith.science/pith/HRBC2HBKDYH2FV5GKMSEZMREME/action/replication_record"}},"created_at":"2026-07-05T08:14:01.987221+00:00","updated_at":"2026-07-05T08:14:01.987221+00:00"}