{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:BXTHG27KXDEBXOS3EHF2PZELBI","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":"47411bb5f1835ba7c0c7c16a4c370026d1b1e5d894f6ec52f0d251ffa6970dba","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-29T03:52:20Z","title_canon_sha256":"ba660c3a07969b5a3cd42f17bdbfe0548ef6ac74b35a9ae2f10d3b3442bd45cf"},"schema_version":"1.0","source":{"id":"1810.00143","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00143","created_at":"2026-05-17T23:42:42Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00143v4","created_at":"2026-05-17T23:42:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00143","created_at":"2026-05-17T23:42:42Z"},{"alias_kind":"pith_short_12","alias_value":"BXTHG27KXDEB","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BXTHG27KXDEBXOS3","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BXTHG27K","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:49d2feb269d05df6026363f7c207a7afe386abd7c44a069d86184a10e79ec5f8","target":"graph","created_at":"2026-05-17T23:42:42Z","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":"Adam is shown not being able to converge to the optimal solution in certain cases. Researchers recently propose several algorithms to avoid the issue of non-convergence of Adam, but their efficiency turns out to be unsatisfactory in practice. In this paper, we provide new insight into the non-convergence issue of Adam as well as other adaptive learning rate methods. We argue that there exists an inappropriate correlation between gradient $g_t$ and the second-moment term $v_t$ in Adam ($t$ is the timestep), which results in that a large gradient is likely to have small step size while a small g","authors_text":"Guansong Lu, Hongwei Wang, Qingru Zhang, Weinan Zhang, Yong Yu, Zhiming Zhou","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-29T03:52:20Z","title":"AdaShift: Decorrelation and Convergence of Adaptive Learning Rate Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00143","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":"sha256:8761a235b828d9aa028a2f75d4ab0853888fc16cb1cf18da7e73ddca60de9336","target":"record","created_at":"2026-05-17T23:42:42Z","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":"47411bb5f1835ba7c0c7c16a4c370026d1b1e5d894f6ec52f0d251ffa6970dba","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-29T03:52:20Z","title_canon_sha256":"ba660c3a07969b5a3cd42f17bdbfe0548ef6ac74b35a9ae2f10d3b3442bd45cf"},"schema_version":"1.0","source":{"id":"1810.00143","kind":"arxiv","version":4}},"canonical_sha256":"0de6736beab8c81bba5b21cba7e48b0a1622a8497f89a698ced344f757c20cd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0de6736beab8c81bba5b21cba7e48b0a1622a8497f89a698ced344f757c20cd1","first_computed_at":"2026-05-17T23:42:42.984496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:42.984496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ju1FOIE6YLuA9fs0NCOW4CFpjHWyjRnt7kJN+UlJCDDYFUAN5+p0sbKxiNqIQrtASv4ZAtguXJ0cQYeaEIB6CA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:42.985156Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.00143","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8761a235b828d9aa028a2f75d4ab0853888fc16cb1cf18da7e73ddca60de9336","sha256:49d2feb269d05df6026363f7c207a7afe386abd7c44a069d86184a10e79ec5f8"],"state_sha256":"40f3d7629e0972c48472bbe4ddf0f199d749c392f390b39217b80b0310132354"}