{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3W73LM64AYQQ46POITXWQ35ETA","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":"ec41c1ecb42f150e461cd3c63218e16d64513016442ec0b90bd81903debe7114","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-16T20:25:28Z","title_canon_sha256":"52a696e6bc19ce389dbf51ec5b820f88bd05b9591931e78e321affb8c1724708"},"schema_version":"1.0","source":{"id":"1808.05671","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.05671","created_at":"2026-07-05T08:34:46Z"},{"alias_kind":"arxiv_version","alias_value":"1808.05671v4","created_at":"2026-07-05T08:34:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.05671","created_at":"2026-07-05T08:34:46Z"},{"alias_kind":"pith_short_12","alias_value":"3W73LM64AYQQ","created_at":"2026-07-05T08:34:46Z"},{"alias_kind":"pith_short_16","alias_value":"3W73LM64AYQQ46PO","created_at":"2026-07-05T08:34:46Z"},{"alias_kind":"pith_short_8","alias_value":"3W73LM64","created_at":"2026-07-05T08:34:46Z"}],"graph_snapshots":[{"event_id":"sha256:5191184e6821c2eb9f6b6ba13b0d35b3517d110e7f20cc523225aebe9b431000","target":"graph","created_at":"2026-07-05T08:34:46Z","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/1808.05671/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adaptive gradient methods are workhorses in deep learning. However, the convergence guarantees of adaptive gradient methods for nonconvex optimization have not been thoroughly studied. In this paper, we provide a fine-grained convergence analysis for a general class of adaptive gradient methods including AMSGrad, RMSProp and AdaGrad. For smooth nonconvex functions, we prove that adaptive gradient methods in expectation converge to a first-order stationary point. Our convergence rate is better than existing results for adaptive gradient methods in terms of dimension. In addition, we also prove ","authors_text":"Dongruo Zhou, Jinghui Chen, Quanquan Gu, Yuan Cao, Ziyan Yang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-16T20:25:28Z","title":"On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.05671","kind":"arxiv","version":4},"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":"sha256:1056defb7894d11d5c10825c1c804078dcba197bff15ecd281f1031a402939d0","target":"record","created_at":"2026-07-05T08:34:46Z","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":"ec41c1ecb42f150e461cd3c63218e16d64513016442ec0b90bd81903debe7114","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-16T20:25:28Z","title_canon_sha256":"52a696e6bc19ce389dbf51ec5b820f88bd05b9591931e78e321affb8c1724708"},"schema_version":"1.0","source":{"id":"1808.05671","kind":"arxiv","version":4}},"canonical_sha256":"ddbfb5b3dc06210e79ee44ef686fa49807946f1fd4745cddf7b14bb5fc9cfc65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddbfb5b3dc06210e79ee44ef686fa49807946f1fd4745cddf7b14bb5fc9cfc65","first_computed_at":"2026-07-05T08:34:46.094826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:46.094826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q5sYNhj/9XZs2ayQLedwLX54tq6VtBrpu0vFgimYbzyTUSlfPGNAE02jlOk8u5C2FUdaIyXCFwpDcMvWZimqDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:46.095307Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.05671","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1056defb7894d11d5c10825c1c804078dcba197bff15ecd281f1031a402939d0","sha256:5191184e6821c2eb9f6b6ba13b0d35b3517d110e7f20cc523225aebe9b431000"],"state_sha256":"479c073c365814babafb06de188e38a5ba319b816d7aea803af1023b7cac03d0"}