{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V2KXUHSDBVZOFAKATKWADGYMQ2","short_pith_number":"pith:V2KXUHSD","schema_version":"1.0","canonical_sha256":"ae957a1e430d72e281409aac019b0c86b3af89e1e0771cb7645c6f652f5be4ef","source":{"kind":"arxiv","id":"2302.06570","version":1},"attestation_state":"computed","paper":{"title":"Beyond Uniform Smoothness: A Stopped Analysis of Adaptive SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Constantine Caramanis, Litu Rout, Matthew Faw, Sanjay Shakkottai","submitted_at":"2023-02-13T18:13:36Z","abstract_excerpt":"This work considers the problem of finding a first-order stationary point of a non-convex function with potentially unbounded smoothness constant using a stochastic gradient oracle. We focus on the class of $(L_0,L_1)$-smooth functions proposed by Zhang et al. (ICLR'20). Empirical evidence suggests that these functions more closely captures practical machine learning problems as compared to the pervasive $L_0$-smoothness. This class is rich enough to include highly non-smooth functions, such as $\\exp(L_1 x)$ which is $(0,\\mathcal{O}(L_1))$-smooth. Despite the richness, an emerging line of work"},"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":"2302.06570","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-02-13T18:13:36Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"a45c11cd25451307716f21bc42a6767fc80d0c1ac6d127d9a0764de2e9a20247","abstract_canon_sha256":"4f008de31d1e9eefa8ceb4c0f008d580345433b2bc764d63407753a8e10d711b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:41:12.520093Z","signature_b64":"V2tMHD/yNe9z2J1BrUbbasU+dxVepdJnXhhE3bSgIvgVqYReSJI+4I3n6KGLl619KH3lmzCgf/BuWic4YikCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae957a1e430d72e281409aac019b0c86b3af89e1e0771cb7645c6f652f5be4ef","last_reissued_at":"2026-07-05T05:41:12.519654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:41:12.519654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Uniform Smoothness: A Stopped Analysis of Adaptive SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Constantine Caramanis, Litu Rout, Matthew Faw, Sanjay Shakkottai","submitted_at":"2023-02-13T18:13:36Z","abstract_excerpt":"This work considers the problem of finding a first-order stationary point of a non-convex function with potentially unbounded smoothness constant using a stochastic gradient oracle. We focus on the class of $(L_0,L_1)$-smooth functions proposed by Zhang et al. (ICLR'20). Empirical evidence suggests that these functions more closely captures practical machine learning problems as compared to the pervasive $L_0$-smoothness. This class is rich enough to include highly non-smooth functions, such as $\\exp(L_1 x)$ which is $(0,\\mathcal{O}(L_1))$-smooth. Despite the richness, an emerging line of work"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06570","kind":"arxiv","version":1},"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/2302.06570/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":"2302.06570","created_at":"2026-07-05T05:41:12.519711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.06570v1","created_at":"2026-07-05T05:41:12.519711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06570","created_at":"2026-07-05T05:41:12.519711+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2KXUHSDBVZO","created_at":"2026-07-05T05:41:12.519711+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2KXUHSDBVZOFAKA","created_at":"2026-07-05T05:41:12.519711+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2KXUHSD","created_at":"2026-07-05T05:41:12.519711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17423","citing_title":"A unified convergence theory for adaptive first-order methods in the nonconvex case, including AdaNorm, full and diagonal AdaGrad, Shampoo and Muo","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V2KXUHSDBVZOFAKATKWADGYMQ2","json":"https://pith.science/pith/V2KXUHSDBVZOFAKATKWADGYMQ2.json","graph_json":"https://pith.science/api/pith-number/V2KXUHSDBVZOFAKATKWADGYMQ2/graph.json","events_json":"https://pith.science/api/pith-number/V2KXUHSDBVZOFAKATKWADGYMQ2/events.json","paper":"https://pith.science/paper/V2KXUHSD"},"agent_actions":{"view_html":"https://pith.science/pith/V2KXUHSDBVZOFAKATKWADGYMQ2","download_json":"https://pith.science/pith/V2KXUHSDBVZOFAKATKWADGYMQ2.json","view_paper":"https://pith.science/paper/V2KXUHSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.06570&json=true","fetch_graph":"https://pith.science/api/pith-number/V2KXUHSDBVZOFAKATKWADGYMQ2/graph.json","fetch_events":"https://pith.science/api/pith-number/V2KXUHSDBVZOFAKATKWADGYMQ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2KXUHSDBVZOFAKATKWADGYMQ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2KXUHSDBVZOFAKATKWADGYMQ2/action/storage_attestation","attest_author":"https://pith.science/pith/V2KXUHSDBVZOFAKATKWADGYMQ2/action/author_attestation","sign_citation":"https://pith.science/pith/V2KXUHSDBVZOFAKATKWADGYMQ2/action/citation_signature","submit_replication":"https://pith.science/pith/V2KXUHSDBVZOFAKATKWADGYMQ2/action/replication_record"}},"created_at":"2026-07-05T05:41:12.519711+00:00","updated_at":"2026-07-05T05:41:12.519711+00:00"}