{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4YIVIUCKTM3Z6GNKP4YSRELALP","short_pith_number":"pith:4YIVIUCK","schema_version":"1.0","canonical_sha256":"e61154504a9b379f19aa7f312891605be2e2db69bc418175a850a2e6eb9bbe32","source":{"kind":"arxiv","id":"2112.03459","version":1},"attestation_state":"computed","paper":{"title":"A Novel Convergence Analysis for Algorithms of the Adam Family","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Rong Jin, Tianbao Yang, Wotao Yin, Yi Xu, Zhishuai Guo","submitted_at":"2021-12-07T02:47:58Z","abstract_excerpt":"Since its invention in 2014, the Adam optimizer has received tremendous attention. On one hand, it has been widely used in deep learning and many variants have been proposed, while on the other hand their theoretical convergence property remains to be a mystery. It is far from satisfactory in the sense that some studies require strong assumptions about the updates, which are not necessarily applicable in practice, while other studies still follow the original problematic convergence analysis of Adam, which was shown to be not sufficient to ensure convergence. Although rigorous convergence anal"},"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":"2112.03459","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T02:47:58Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"93309bcd145270c5c6edb7ce0146434e8a22d61aca0393e372a5f5b61023af5e","abstract_canon_sha256":"eb725846596026b601fdeaadd813640c087dbeab0c4978b06030d0a4dc8170e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:45.799404Z","signature_b64":"aa8GCkxKD8IIKvirCioHDDrlkk2PZzEc0zfcnWz5KP/IDvWz0v12LqWRp4YHasRuLAF/+50491a05N6jtyKFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e61154504a9b379f19aa7f312891605be2e2db69bc418175a850a2e6eb9bbe32","last_reissued_at":"2026-07-05T03:38:45.798957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:45.798957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Novel Convergence Analysis for Algorithms of the Adam Family","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Rong Jin, Tianbao Yang, Wotao Yin, Yi Xu, Zhishuai Guo","submitted_at":"2021-12-07T02:47:58Z","abstract_excerpt":"Since its invention in 2014, the Adam optimizer has received tremendous attention. On one hand, it has been widely used in deep learning and many variants have been proposed, while on the other hand their theoretical convergence property remains to be a mystery. It is far from satisfactory in the sense that some studies require strong assumptions about the updates, which are not necessarily applicable in practice, while other studies still follow the original problematic convergence analysis of Adam, which was shown to be not sufficient to ensure convergence. Although rigorous convergence anal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03459","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/2112.03459/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":"2112.03459","created_at":"2026-07-05T03:38:45.799011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.03459v1","created_at":"2026-07-05T03:38:45.799011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03459","created_at":"2026-07-05T03:38:45.799011+00:00"},{"alias_kind":"pith_short_12","alias_value":"4YIVIUCKTM3Z","created_at":"2026-07-05T03:38:45.799011+00:00"},{"alias_kind":"pith_short_16","alias_value":"4YIVIUCKTM3Z6GNK","created_at":"2026-07-05T03:38:45.799011+00:00"},{"alias_kind":"pith_short_8","alias_value":"4YIVIUCK","created_at":"2026-07-05T03:38:45.799011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17526","citing_title":"MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04662","citing_title":"Why Muon Outperforms Adam: A Curvature Perspective","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2409.04777","citing_title":"Optimization Hyper-parameter Laws for Large Language Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03099","citing_title":"Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15816","citing_title":"On the Convergence of Muon and Beyond","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03099","citing_title":"Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10288","citing_title":"BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10288","citing_title":"BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15392","citing_title":"Lightweight Geometric Adaptation for Training Physics-Informed Neural Networks","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4YIVIUCKTM3Z6GNKP4YSRELALP","json":"https://pith.science/pith/4YIVIUCKTM3Z6GNKP4YSRELALP.json","graph_json":"https://pith.science/api/pith-number/4YIVIUCKTM3Z6GNKP4YSRELALP/graph.json","events_json":"https://pith.science/api/pith-number/4YIVIUCKTM3Z6GNKP4YSRELALP/events.json","paper":"https://pith.science/paper/4YIVIUCK"},"agent_actions":{"view_html":"https://pith.science/pith/4YIVIUCKTM3Z6GNKP4YSRELALP","download_json":"https://pith.science/pith/4YIVIUCKTM3Z6GNKP4YSRELALP.json","view_paper":"https://pith.science/paper/4YIVIUCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.03459&json=true","fetch_graph":"https://pith.science/api/pith-number/4YIVIUCKTM3Z6GNKP4YSRELALP/graph.json","fetch_events":"https://pith.science/api/pith-number/4YIVIUCKTM3Z6GNKP4YSRELALP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4YIVIUCKTM3Z6GNKP4YSRELALP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4YIVIUCKTM3Z6GNKP4YSRELALP/action/storage_attestation","attest_author":"https://pith.science/pith/4YIVIUCKTM3Z6GNKP4YSRELALP/action/author_attestation","sign_citation":"https://pith.science/pith/4YIVIUCKTM3Z6GNKP4YSRELALP/action/citation_signature","submit_replication":"https://pith.science/pith/4YIVIUCKTM3Z6GNKP4YSRELALP/action/replication_record"}},"created_at":"2026-07-05T03:38:45.799011+00:00","updated_at":"2026-07-05T03:38:45.799011+00:00"}