{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3W73LM64AYQQ46POITXWQ35ETA","short_pith_number":"pith:3W73LM64","canonical_record":{"source":{"id":"1808.05671","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-16T20:25:28Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"52a696e6bc19ce389dbf51ec5b820f88bd05b9591931e78e321affb8c1724708","abstract_canon_sha256":"ec41c1ecb42f150e461cd3c63218e16d64513016442ec0b90bd81903debe7114"},"schema_version":"1.0"},"canonical_sha256":"ddbfb5b3dc06210e79ee44ef686fa49807946f1fd4745cddf7b14bb5fc9cfc65","source":{"kind":"arxiv","id":"1808.05671","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3W73LM64AYQQ46POITXWQ35ETA","target":"record","payload":{"canonical_record":{"source":{"id":"1808.05671","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-16T20:25:28Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"52a696e6bc19ce389dbf51ec5b820f88bd05b9591931e78e321affb8c1724708","abstract_canon_sha256":"ec41c1ecb42f150e461cd3c63218e16d64513016442ec0b90bd81903debe7114"},"schema_version":"1.0"},"canonical_sha256":"ddbfb5b3dc06210e79ee44ef686fa49807946f1fd4745cddf7b14bb5fc9cfc65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:46.095307Z","signature_b64":"q5sYNhj/9XZs2ayQLedwLX54tq6VtBrpu0vFgimYbzyTUSlfPGNAE02jlOk8u5C2FUdaIyXCFwpDcMvWZimqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddbfb5b3dc06210e79ee44ef686fa49807946f1fd4745cddf7b14bb5fc9cfc65","last_reissued_at":"2026-07-05T08:34:46.094826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:46.094826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.05671","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:34:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FF8r6WaLML6eBlxjU81IDQZ/Chze1qVwlJlqDgyOL8pHywsaIF5v3XxETCD0VgNXTRB7lJml8aJ4VZNo5NBMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:49:44.829236Z"},"content_sha256":"1056defb7894d11d5c10825c1c804078dcba197bff15ecd281f1031a402939d0","schema_version":"1.0","event_id":"sha256:1056defb7894d11d5c10825c1c804078dcba197bff15ecd281f1031a402939d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3W73LM64AYQQ46POITXWQ35ETA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Jinghui Chen, Quanquan Gu, Yuan Cao, Ziyan Yang","submitted_at":"2018-08-16T20:25:28Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.05671","kind":"arxiv","version":4},"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/1808.05671/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:34:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xawZQt2J5j4L0xbxXgqBO0bhBYjngvED5DAKyOPFYOGOj0bEkZkJo6PEiDHcdsO5s76U9GOUwb1QT+CgpQD6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:49:44.829739Z"},"content_sha256":"5191184e6821c2eb9f6b6ba13b0d35b3517d110e7f20cc523225aebe9b431000","schema_version":"1.0","event_id":"sha256:5191184e6821c2eb9f6b6ba13b0d35b3517d110e7f20cc523225aebe9b431000"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3W73LM64AYQQ46POITXWQ35ETA/bundle.json","state_url":"https://pith.science/pith/3W73LM64AYQQ46POITXWQ35ETA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3W73LM64AYQQ46POITXWQ35ETA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T23:49:44Z","links":{"resolver":"https://pith.science/pith/3W73LM64AYQQ46POITXWQ35ETA","bundle":"https://pith.science/pith/3W73LM64AYQQ46POITXWQ35ETA/bundle.json","state":"https://pith.science/pith/3W73LM64AYQQ46POITXWQ35ETA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3W73LM64AYQQ46POITXWQ35ETA/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iEPjwoQ9JiYNvKGAfRf7XWMLwu/qp4gh/XxCl+AWRhn7qx3ANBu+kP084nN3PMW/IS/2cWckQmb6MxXHysILAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:49:44.834662Z","bundle_sha256":"0f3c45e6fae04af4a27864be1d6b922ec1f951026267750f4b0f07641c29e855"}}