{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CRXAS6CXITJJYCI73QKNVBVIVR","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":"2890904b9172f6a7dfb98d1a9f54e4650e62b00fd60e28fb7418082b2f91b717","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-02-01T07:21:32Z","title_canon_sha256":"68fef912bdbd60b2886c8a8be660ef11ca83744d854c9d8a6e84a6acfe1ce5fc"},"schema_version":"1.0","source":{"id":"2402.00389","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.00389","created_at":"2026-07-05T10:54:11Z"},{"alias_kind":"arxiv_version","alias_value":"2402.00389v5","created_at":"2026-07-05T10:54:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00389","created_at":"2026-07-05T10:54:11Z"},{"alias_kind":"pith_short_12","alias_value":"CRXAS6CXITJJ","created_at":"2026-07-05T10:54:11Z"},{"alias_kind":"pith_short_16","alias_value":"CRXAS6CXITJJYCI7","created_at":"2026-07-05T10:54:11Z"},{"alias_kind":"pith_short_8","alias_value":"CRXAS6CX","created_at":"2026-07-05T10:54:11Z"}],"graph_snapshots":[{"event_id":"sha256:635d9a449db5da630c87c293b2c83f44c8fe020aa7cdf095449a71939d654829","target":"graph","created_at":"2026-07-05T10:54:11Z","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/2402.00389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although adaptive gradient methods have been extensively used in deep learning, their convergence rates proved in the literature are all slower than that of SGD, particularly with respect to their dependence on the dimension. This paper considers the classical RMSProp and its momentum extension and establishes the convergence rate of $\\frac{1}{T}\\sum_{k=1}^T E\\left[\\|\\nabla f(x^k)\\|_1\\right]\\leq O(\\frac{\\sqrt{d}C}{T^{1/4}})$ measured by $\\ell_1$ norm without the bounded gradient assumption, where $d$ is the dimension of the optimization variable, $T$ is the iteration number, and $C$ is a const","authors_text":"Huan Li, Yiming Dong, Zhouchen Lin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-02-01T07:21:32Z","title":"On the $O(\\frac{\\sqrt{d}}{T^{1/4}})$ Convergence Rate of RMSProp and Its Momentum Extension Measured by $\\ell_1$ Norm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00389","kind":"arxiv","version":5},"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":"sha256:143eee4bb0d759b986d62423f0e135573cd3cbe66bb6423ba823fd19a00f5810","target":"record","created_at":"2026-07-05T10:54:11Z","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":"2890904b9172f6a7dfb98d1a9f54e4650e62b00fd60e28fb7418082b2f91b717","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-02-01T07:21:32Z","title_canon_sha256":"68fef912bdbd60b2886c8a8be660ef11ca83744d854c9d8a6e84a6acfe1ce5fc"},"schema_version":"1.0","source":{"id":"2402.00389","kind":"arxiv","version":5}},"canonical_sha256":"146e09785744d29c091fdc14da86a8ac4d24cf5ecb0fe265d1cc1435820cec24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"146e09785744d29c091fdc14da86a8ac4d24cf5ecb0fe265d1cc1435820cec24","first_computed_at":"2026-07-05T10:54:11.057758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:11.057758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pKtwEGji4iPXD+dYsEBiAmfZO8qaKcpx2mXw2uQTEjpeX40p8gR45Rbr1o9fdve3i9MlW1sg201J9+OfbFabCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:11.058223Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.00389","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:143eee4bb0d759b986d62423f0e135573cd3cbe66bb6423ba823fd19a00f5810","sha256:635d9a449db5da630c87c293b2c83f44c8fe020aa7cdf095449a71939d654829"],"state_sha256":"c6d1830671885443a1293a732eb5fc7e569f081b4b80da99962c5287867778a9"}