{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KPANOW7K4PKSVVMAMDL6FXVQKA","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":"5a6018aca80e8d560e399105cda5ded14b83b317de51e380a046a39b1f8d642c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T06:57:47Z","title_canon_sha256":"f683e49eb1e993885d8602eaf2279675decc97b4fa2cfb10c53ee2332fa21581"},"schema_version":"1.0","source":{"id":"2411.02853","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02853","created_at":"2026-07-05T09:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02853v3","created_at":"2026-07-05T09:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02853","created_at":"2026-07-05T09:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"KPANOW7K4PKS","created_at":"2026-07-05T09:38:50Z"},{"alias_kind":"pith_short_16","alias_value":"KPANOW7K4PKSVVMA","created_at":"2026-07-05T09:38:50Z"},{"alias_kind":"pith_short_8","alias_value":"KPANOW7K","created_at":"2026-07-05T09:38:50Z"}],"graph_snapshots":[{"event_id":"sha256:c6a486d33e838b8368b6e81533bc6aa570fa72f02320e2ead401eae83ec1b585","target":"graph","created_at":"2026-07-05T09:38:50Z","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/2411.02853/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Go Nagahara, Gouki Minegishi, Keno Harada, Masahiro Suzuki, Seong Cheol Jeong, Shohei Taniguchi, Tomoshi Iiyama, Yusuke Iwasawa, Yutaka Matsuo, Yuta Oshima","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T06:57:47Z","title":"ADOPT: Modified Adam Can Converge with Any $\\beta_2$ with the Optimal Rate"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02853","kind":"arxiv","version":3},"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":"sha256:8dee35430f639922b86f331ae7128d2890bbcd9ad59ce144b75a1707c0b82325","target":"record","created_at":"2026-07-05T09:38:50Z","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":"5a6018aca80e8d560e399105cda5ded14b83b317de51e380a046a39b1f8d642c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T06:57:47Z","title_canon_sha256":"f683e49eb1e993885d8602eaf2279675decc97b4fa2cfb10c53ee2332fa21581"},"schema_version":"1.0","source":{"id":"2411.02853","kind":"arxiv","version":3}},"canonical_sha256":"53c0d75beae3d52ad58060d7e2deb050235918de5f9bb3dfc50576bf853c6b2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53c0d75beae3d52ad58060d7e2deb050235918de5f9bb3dfc50576bf853c6b2d","first_computed_at":"2026-07-05T09:38:50.465069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:50.465069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e3d8hU7FG/VOdR6JfBu27nbjYSzsEUNCNT5cjFo33VJgcOZCVEjx1yH1WCNj+aXZ4Ah4fs6khFM1AXWbYJ+tCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:50.465574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.02853","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dee35430f639922b86f331ae7128d2890bbcd9ad59ce144b75a1707c0b82325","sha256:c6a486d33e838b8368b6e81533bc6aa570fa72f02320e2ead401eae83ec1b585"],"state_sha256":"a956aba9ec686828484d0410d33e2d7f818336c5971775305c0388ce03f9f85a"}