{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4ZALQAHJ6MS3W7GNOGP5ZYCRH7","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":"13d3ea94ed91ca6a6fa07f9ac831e3699a27bb2b78f18db5da4c1a903572844a","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-26T03:12:14Z","title_canon_sha256":"10a6c0db9bcbb7fa04b899f99b117f97c55a4c27a1e3a09bb15e8a9d236f7a5e"},"schema_version":"1.0","source":{"id":"1901.09149","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09149","created_at":"2026-07-05T00:37:43Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09149v2","created_at":"2026-07-05T00:37:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09149","created_at":"2026-07-05T00:37:43Z"},{"alias_kind":"pith_short_12","alias_value":"4ZALQAHJ6MS3","created_at":"2026-07-05T00:37:43Z"},{"alias_kind":"pith_short_16","alias_value":"4ZALQAHJ6MS3W7GN","created_at":"2026-07-05T00:37:43Z"},{"alias_kind":"pith_short_8","alias_value":"4ZALQAHJ","created_at":"2026-07-05T00:37:43Z"}],"graph_snapshots":[{"event_id":"sha256:b52b0a480e223c205f2375b4bb1d7e91df1ea9ce26fce8910e8277fda09f7c32","target":"graph","created_at":"2026-07-05T00:37:43Z","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/1901.09149/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adaptive methods such as Adam and RMSProp are widely used in deep learning but are not well understood. In this paper, we seek a crisp, clean and precise characterization of their behavior in nonconvex settings. To this end, we first provide a novel view of adaptive methods as preconditioned SGD, where the preconditioner is estimated in an online manner. By studying the preconditioner on its own, we elucidate its purpose: it rescales the stochastic gradient noise to be isotropic near stationary points, which helps escape saddle points. Furthermore, we show that adaptive methods can efficiently","authors_text":"Matthew Staib, Sanjiv Kumar, Sashank J. Reddi, Satyen Kale, Suvrit Sra","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-26T03:12:14Z","title":"Escaping Saddle Points with Adaptive Gradient Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09149","kind":"arxiv","version":2},"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":"sha256:4fc5f1205b4cba1128de06a306e525533d6fc15542aa75120310bed270bf9062","target":"record","created_at":"2026-07-05T00:37:43Z","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":"13d3ea94ed91ca6a6fa07f9ac831e3699a27bb2b78f18db5da4c1a903572844a","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-26T03:12:14Z","title_canon_sha256":"10a6c0db9bcbb7fa04b899f99b117f97c55a4c27a1e3a09bb15e8a9d236f7a5e"},"schema_version":"1.0","source":{"id":"1901.09149","kind":"arxiv","version":2}},"canonical_sha256":"e640b800e9f325bb7ccd719fdce0513ff81a50cb94e82c791e5b48ece137f564","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e640b800e9f325bb7ccd719fdce0513ff81a50cb94e82c791e5b48ece137f564","first_computed_at":"2026-07-05T00:37:43.998704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:37:43.998704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o5sWK2n0drzMz8cN8bZ23RY0cmo7vuhQLNIeWX5A/C9mem1H0r1nHNKUa0+YeC49AL8XDkls1DvQfjOQISPVBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:37:43.999098Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.09149","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fc5f1205b4cba1128de06a306e525533d6fc15542aa75120310bed270bf9062","sha256:b52b0a480e223c205f2375b4bb1d7e91df1ea9ce26fce8910e8277fda09f7c32"],"state_sha256":"bd555d785fc593fb44bfc3c71b2665bd1fbc82d30a77d043212cc5c3860b1052"}