{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6JDLNKJQBSDVHMASZP3JINFQY6","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":"fb8408995c961b3e564af880adee8909f209a4266e735bcc1d441368f64732f2","cross_cats_sorted":["cs.CV","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-14T03:32:54Z","title_canon_sha256":"12c6cf4d6e6a1024c924312f4ffe34a16120ac8a53ae81fe62136825a766a00e"},"schema_version":"1.0","source":{"id":"2412.10663","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10663","created_at":"2026-07-05T10:29:28Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10663v2","created_at":"2026-07-05T10:29:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10663","created_at":"2026-07-05T10:29:28Z"},{"alias_kind":"pith_short_12","alias_value":"6JDLNKJQBSDV","created_at":"2026-07-05T10:29:28Z"},{"alias_kind":"pith_short_16","alias_value":"6JDLNKJQBSDVHMAS","created_at":"2026-07-05T10:29:28Z"},{"alias_kind":"pith_short_8","alias_value":"6JDLNKJQ","created_at":"2026-07-05T10:29:28Z"}],"graph_snapshots":[{"event_id":"sha256:162e0ada31200094eaea5b5cd37c08cd2e7067f92f0570e01ef54a0150fea8ef","target":"graph","created_at":"2026-07-05T10:29:28Z","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/2412.10663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preconditioned stochastic optimization algorithms, exemplified by Shampoo, outperform first-order optimizers by offering theoretical convergence benefits and practical gains in large-scale neural network training. However, they incur substantial memory overhead due to the storage demands of non-diagonal preconditioning matrices. To address this, we introduce 4-bit quantization for Shampoo's preconditioners. We introduce two key methods: First, we apply Cholesky decomposition followed by quantization of the Cholesky factors, reducing memory usage by leveraging their lower triangular structure w","authors_text":"Jingyang Li, Kim-Chuan Toh, Kuangyu Ding, Pan Zhou","cross_cats":["cs.CV","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-14T03:32:54Z","title":"Memory-Efficient 4-bit Preconditioned Stochastic Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10663","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":"sha256:4fdaf3f79b3b34bec6e74d2a0a4df0ddd14515540a621e1b3cf029b8dfb6296a","target":"record","created_at":"2026-07-05T10:29:28Z","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":"fb8408995c961b3e564af880adee8909f209a4266e735bcc1d441368f64732f2","cross_cats_sorted":["cs.CV","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-14T03:32:54Z","title_canon_sha256":"12c6cf4d6e6a1024c924312f4ffe34a16120ac8a53ae81fe62136825a766a00e"},"schema_version":"1.0","source":{"id":"2412.10663","kind":"arxiv","version":2}},"canonical_sha256":"f246b6a9300c8753b012cbf69434b0c798397ebcb345b5b39b7a1ef1c311f5b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f246b6a9300c8753b012cbf69434b0c798397ebcb345b5b39b7a1ef1c311f5b9","first_computed_at":"2026-07-05T10:29:28.518110Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:28.518110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Ag+o2MC/tKJjRXusgZh0gVvhT6pkIVCElDrRDz3jHvgjUchFNvGzOfOtqmxiHsCeeqUy7Tuj/eY0ns+KlX0Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:28.518807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10663","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fdaf3f79b3b34bec6e74d2a0a4df0ddd14515540a621e1b3cf029b8dfb6296a","sha256:162e0ada31200094eaea5b5cd37c08cd2e7067f92f0570e01ef54a0150fea8ef"],"state_sha256":"da96ca0357b26e7267f44b4e315ed7a80c99fa119ed4194b19f9bca96332bf25"}