{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HRBC2HBKDYH2FV5GKMSEZMREME","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"590214d8e50752d48dc828d9ee396f8675246e963c1f23f0df11324df2f54d3b","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-28T18:53:41Z","title_canon_sha256":"f675822d539980b1f9e693c44dd1c412c1b6a84f605ab27e5af9544fe6b78f89"},"schema_version":"1.0","source":{"id":"2310.18784","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.18784","created_at":"2026-07-05T08:14:01Z"},{"alias_kind":"arxiv_version","alias_value":"2310.18784v7","created_at":"2026-07-05T08:14:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18784","created_at":"2026-07-05T08:14:01Z"},{"alias_kind":"pith_short_12","alias_value":"HRBC2HBKDYH2","created_at":"2026-07-05T08:14:01Z"},{"alias_kind":"pith_short_16","alias_value":"HRBC2HBKDYH2FV5G","created_at":"2026-07-05T08:14:01Z"},{"alias_kind":"pith_short_8","alias_value":"HRBC2HBK","created_at":"2026-07-05T08:14:01Z"}],"graph_snapshots":[{"event_id":"sha256:1788456021c18d952d54c1a3a354c393554f704b8c8ac41be4c08960a548b4fc","target":"graph","created_at":"2026-07-05T08:14:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.18784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aleksandar Armacki, Dragana Bajovic, Dusan Jakovetic, Gauri Joshi, Pranay Sharma, Soummya Kar","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-28T18:53:41Z","title":"High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18784","kind":"arxiv","version":7},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:29515cee21f4d7689ee11fc2ab6954305d204f9006aa5e5148ace6eb7b7817a6","target":"record","created_at":"2026-07-05T08:14:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"590214d8e50752d48dc828d9ee396f8675246e963c1f23f0df11324df2f54d3b","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-28T18:53:41Z","title_canon_sha256":"f675822d539980b1f9e693c44dd1c412c1b6a84f605ab27e5af9544fe6b78f89"},"schema_version":"1.0","source":{"id":"2310.18784","kind":"arxiv","version":7}},"canonical_sha256":"3c422d1c2a1e0fa2d7a653244cb2246111ccbc8654b139960efae19a886c5f91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c422d1c2a1e0fa2d7a653244cb2246111ccbc8654b139960efae19a886c5f91","first_computed_at":"2026-07-05T08:14:01.987173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:14:01.987173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"23B407xeScmnQj8Prlt1jfWu/LhjKCNzQ90loqVpMl8cnLIwAzYCQ3lzFljGFeY9ZirKkgZkOOQT/ETegKTCBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:14:01.987619Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.18784","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29515cee21f4d7689ee11fc2ab6954305d204f9006aa5e5148ace6eb7b7817a6","sha256:1788456021c18d952d54c1a3a354c393554f704b8c8ac41be4c08960a548b4fc"],"state_sha256":"5cc14dd598b2b699b57bdaf4d49c5b3af31bf58de424797e6c0ae80224023c24"}