{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KPANOW7K4PKSVVMAMDL6FXVQKA","short_pith_number":"pith:KPANOW7K","schema_version":"1.0","canonical_sha256":"53c0d75beae3d52ad58060d7e2deb050235918de5f9bb3dfc50576bf853c6b2d","source":{"kind":"arxiv","id":"2411.02853","version":3},"attestation_state":"computed","paper":{"title":"ADOPT: Modified Adam Can Converge with Any $\\beta_2$ with the Optimal Rate","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Go Nagahara, Gouki Minegishi, Keno Harada, Masahiro Suzuki, Seong Cheol Jeong, Shohei Taniguchi, Tomoshi Iiyama, Yusuke Iwasawa, Yutaka Matsuo, Yuta Oshima","submitted_at":"2024-11-05T06:57:47Z","abstract_excerpt":"Adam is one of the most popular optimization algorithms in deep learning. However, it is known that Adam does not converge in theory unless choosing a hyperparameter, i.e., $\\beta_2$, in a problem-dependent manner. There have been many attempts to fix the non-convergence (e.g., AMSGrad), but they require an impractical assumption that the gradient noise is uniformly bounded. In this paper, we propose a new adaptive gradient method named ADOPT, which achieves the optimal convergence rate of $\\mathcal{O} ( 1 / \\sqrt{T} )$ with any choice of $\\beta_2$ without depending on the bounded noise assump"},"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":"2411.02853","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T06:57:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f683e49eb1e993885d8602eaf2279675decc97b4fa2cfb10c53ee2332fa21581","abstract_canon_sha256":"5a6018aca80e8d560e399105cda5ded14b83b317de51e380a046a39b1f8d642c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:50.465574Z","signature_b64":"e3d8hU7FG/VOdR6JfBu27nbjYSzsEUNCNT5cjFo33VJgcOZCVEjx1yH1WCNj+aXZ4Ah4fs6khFM1AXWbYJ+tCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53c0d75beae3d52ad58060d7e2deb050235918de5f9bb3dfc50576bf853c6b2d","last_reissued_at":"2026-07-05T09:38:50.465069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:50.465069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ADOPT: Modified Adam Can Converge with Any $\\beta_2$ with the Optimal Rate","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Go Nagahara, Gouki Minegishi, Keno Harada, Masahiro Suzuki, Seong Cheol Jeong, Shohei Taniguchi, Tomoshi Iiyama, Yusuke Iwasawa, Yutaka Matsuo, Yuta Oshima","submitted_at":"2024-11-05T06:57:47Z","abstract_excerpt":"Adam is one of the most popular optimization algorithms in deep learning. However, it is known that Adam does not converge in theory unless choosing a hyperparameter, i.e., $\\beta_2$, in a problem-dependent manner. There have been many attempts to fix the non-convergence (e.g., AMSGrad), but they require an impractical assumption that the gradient noise is uniformly bounded. In this paper, we propose a new adaptive gradient method named ADOPT, which achieves the optimal convergence rate of $\\mathcal{O} ( 1 / \\sqrt{T} )$ with any choice of $\\beta_2$ without depending on the bounded noise assump"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02853","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/2411.02853/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":"2411.02853","created_at":"2026-07-05T09:38:50.465141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.02853v3","created_at":"2026-07-05T09:38:50.465141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02853","created_at":"2026-07-05T09:38:50.465141+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPANOW7K4PKS","created_at":"2026-07-05T09:38:50.465141+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPANOW7K4PKSVVMA","created_at":"2026-07-05T09:38:50.465141+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPANOW7K","created_at":"2026-07-05T09:38:50.465141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.18900","citing_title":"Foundation Models for Discovery and Exploration in Chemical Space","ref_index":147,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12878","citing_title":"Adam-SHANG: A Convergent Adam-Type Method for Stochastic Smooth Convex Optimization","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPANOW7K4PKSVVMAMDL6FXVQKA","json":"https://pith.science/pith/KPANOW7K4PKSVVMAMDL6FXVQKA.json","graph_json":"https://pith.science/api/pith-number/KPANOW7K4PKSVVMAMDL6FXVQKA/graph.json","events_json":"https://pith.science/api/pith-number/KPANOW7K4PKSVVMAMDL6FXVQKA/events.json","paper":"https://pith.science/paper/KPANOW7K"},"agent_actions":{"view_html":"https://pith.science/pith/KPANOW7K4PKSVVMAMDL6FXVQKA","download_json":"https://pith.science/pith/KPANOW7K4PKSVVMAMDL6FXVQKA.json","view_paper":"https://pith.science/paper/KPANOW7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.02853&json=true","fetch_graph":"https://pith.science/api/pith-number/KPANOW7K4PKSVVMAMDL6FXVQKA/graph.json","fetch_events":"https://pith.science/api/pith-number/KPANOW7K4PKSVVMAMDL6FXVQKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPANOW7K4PKSVVMAMDL6FXVQKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPANOW7K4PKSVVMAMDL6FXVQKA/action/storage_attestation","attest_author":"https://pith.science/pith/KPANOW7K4PKSVVMAMDL6FXVQKA/action/author_attestation","sign_citation":"https://pith.science/pith/KPANOW7K4PKSVVMAMDL6FXVQKA/action/citation_signature","submit_replication":"https://pith.science/pith/KPANOW7K4PKSVVMAMDL6FXVQKA/action/replication_record"}},"created_at":"2026-07-05T09:38:50.465141+00:00","updated_at":"2026-07-05T09:38:50.465141+00:00"}