{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OORJVZ5SHIZ4RFXABXVJVDBJKF","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":"8f0700c3fc5ab4964dbcf27de37cbfe64391819584fdc64c115a5fc366a93cf4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T16:56:41Z","title_canon_sha256":"180e4529aa33b034a6053cd8a1ffd3ab8318ad15147a3565453d54090f5b6e0c"},"schema_version":"1.0","source":{"id":"2406.16793","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16793","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16793v7","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16793","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"pith_short_12","alias_value":"OORJVZ5SHIZ4","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"pith_short_16","alias_value":"OORJVZ5SHIZ4RFXA","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"pith_short_8","alias_value":"OORJVZ5S","created_at":"2026-07-05T10:18:38Z"}],"graph_snapshots":[{"event_id":"sha256:d1c2cfa6f3b8e30f34ecfbc5f5688edca6656919dc3b83ae48b73baca636d889","target":"graph","created_at":"2026-07-05T10:18:38Z","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/2406.16793/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Adam-mini, an optimizer that achieves on par or better performance than AdamW with 50% less memory footprint. Adam-mini reduces memory by cutting down the learning rate resources in Adam (i.e., $1/\\sqrt{v}$). By investigating the Hessian structure of neural nets, we find Adam's $v$ might not function at its full potential as effectively as we expected. We find that $\\geq$ 99.9% of these learning rates in $v$ could be harmlessly removed if we (1) carefully partition the parameters into blocks following our new principle on Hessian structure; (2) assign a single but good learning rate","authors_text":"Chenwei Wu, Congliang Chen, Diederik P. Kingma, Ruoyu Sun, Tian Ding, Yinyu Ye, Yushun Zhang, Zhi-Quan Luo, Ziniu Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T16:56:41Z","title":"Adam-mini: Use Fewer Learning Rates To Gain More"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16793","kind":"arxiv","version":7},"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":"sha256:1396f6df5b8d7170e732e9c5ce58ae4f3238f751e2ece1166d767549b9d6f32c","target":"record","created_at":"2026-07-05T10:18:38Z","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":"8f0700c3fc5ab4964dbcf27de37cbfe64391819584fdc64c115a5fc366a93cf4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T16:56:41Z","title_canon_sha256":"180e4529aa33b034a6053cd8a1ffd3ab8318ad15147a3565453d54090f5b6e0c"},"schema_version":"1.0","source":{"id":"2406.16793","kind":"arxiv","version":7}},"canonical_sha256":"73a29ae7b23a33c896e00dea9a8c29517c6f41ff5560a2670a5002e59c4e8a2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73a29ae7b23a33c896e00dea9a8c29517c6f41ff5560a2670a5002e59c4e8a2b","first_computed_at":"2026-07-05T10:18:38.789399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:38.789399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5k3lte3mR7hBFO0jdobNvb2OpN0Sajzehe+Ku/92vCo4ps+mtjjj99r+Pn7bpNUsP9A0cERpZRG7A1StaE53Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:38.789966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.16793","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1396f6df5b8d7170e732e9c5ce58ae4f3238f751e2ece1166d767549b9d6f32c","sha256:d1c2cfa6f3b8e30f34ecfbc5f5688edca6656919dc3b83ae48b73baca636d889"],"state_sha256":"29dc883ca1a82bdbeb0110a161f561f7fad64065d28552f9de0523561f76e3d2"}