{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NAC62DBTP6WY4EWWSCR4OUM4IX","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":"60105a2d8716f6d93b8eae7ae7a0f267b98a9741432f708151ec04b7892e1730","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-19T16:21:38Z","title_canon_sha256":"001a4bb98f91b0563412da3a3e0ea9a3c9d07dfc27c216809c1a47144e79d99e"},"schema_version":"1.0","source":{"id":"1904.09237","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09237","created_at":"2026-05-17T23:48:07Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09237v1","created_at":"2026-05-17T23:48:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09237","created_at":"2026-05-17T23:48:07Z"},{"alias_kind":"pith_short_12","alias_value":"NAC62DBTP6WY","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NAC62DBTP6WY4EWW","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NAC62DBT","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:1fcc29bad1f917351144a1daffd9ebeffb8f6308b6bbb3ab585e2365b8f7b2db","target":"graph","created_at":"2026-05-17T23:48:07Z","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"},"paper":{"abstract_excerpt":"Several recently proposed stochastic optimization methods that have been successfully used in training deep networks such as RMSProp, Adam, Adadelta, Nadam are based on using gradient updates scaled by square roots of exponential moving averages of squared past gradients. In many applications, e.g. learning with large output spaces, it has been empirically observed that these algorithms fail to converge to an optimal solution (or a critical point in nonconvex settings). We show that one cause for such failures is the exponential moving average used in the algorithms. We provide an explicit exa","authors_text":"Sanjiv Kumar, Sashank J. Reddi, Satyen Kale","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-19T16:21:38Z","title":"On the Convergence of Adam and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09237","kind":"arxiv","version":1},"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":"sha256:8d32f577d8f80af754164ea2bb446fd7679f57bf959b8a5c2a634267936ba7b7","target":"record","created_at":"2026-05-17T23:48:07Z","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":"60105a2d8716f6d93b8eae7ae7a0f267b98a9741432f708151ec04b7892e1730","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-19T16:21:38Z","title_canon_sha256":"001a4bb98f91b0563412da3a3e0ea9a3c9d07dfc27c216809c1a47144e79d99e"},"schema_version":"1.0","source":{"id":"1904.09237","kind":"arxiv","version":1}},"canonical_sha256":"6805ed0c337fad8e12d690a3c7519c45ce8a2669ba4baa4d6986435188dd3d65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6805ed0c337fad8e12d690a3c7519c45ce8a2669ba4baa4d6986435188dd3d65","first_computed_at":"2026-05-17T23:48:07.910468Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:07.910468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gHkFA12ruy49vkvg+jlTBvZU96jV6NOp1+n/EwUhr/MSUUl27NUHAKmI3vU4xJXSzy2M4xtBYbleVwkHsDZ4DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:07.910892Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.09237","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d32f577d8f80af754164ea2bb446fd7679f57bf959b8a5c2a634267936ba7b7","sha256:1fcc29bad1f917351144a1daffd9ebeffb8f6308b6bbb3ab585e2365b8f7b2db"],"state_sha256":"87e0cedefc393d47225ff5defe5e32665f4839fd3a681585bab5cf78d8d5f9e7"}