{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IYHWGC3FVITNJHE2HKKPOXTFX2","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":"acf196fa014f2c358fe7b80ca3cdbbfc37e6d17a27e0372a5eb3f25ab39b88c6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-01-12T08:51:03Z","title_canon_sha256":"69c3092ca2f2c829965d7a48a0aa50ef530a4f53d345f7b0a9bedd43b5260bb4"},"schema_version":"1.0","source":{"id":"2601.07326","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.07326","created_at":"2026-05-26T02:04:02Z"},{"alias_kind":"arxiv_version","alias_value":"2601.07326v3","created_at":"2026-05-26T02:04:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.07326","created_at":"2026-05-26T02:04:02Z"},{"alias_kind":"pith_short_12","alias_value":"IYHWGC3FVITN","created_at":"2026-05-26T02:04:02Z"},{"alias_kind":"pith_short_16","alias_value":"IYHWGC3FVITNJHE2","created_at":"2026-05-26T02:04:02Z"},{"alias_kind":"pith_short_8","alias_value":"IYHWGC3F","created_at":"2026-05-26T02:04:02Z"}],"graph_snapshots":[{"event_id":"sha256:f55ef13fca0808fef63eb47196d46ec7d632379b779750036d1873e729889ef6","target":"graph","created_at":"2026-05-26T02:04:02Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our analysis unifies one-sided and two-sided preconditioning and establishes the convergence rate 1/K sum_{k=1}^K E[||nabla f(X_k)||_*] <= O(sqrt(m+n) C / K^{1/4}) measured by nuclear norm."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The derivation relies on standard stochastic-optimization assumptions (smoothness, bounded variance or similar) together with the specific form of the AdamW-style preconditioner; the abstract does not list the precise conditions under which the nuclear-norm bound holds."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"AdamW-style Shampoo unifies one- and two-sided preconditioning and achieves convergence rate O(sqrt(m+n) C / K^{1/4}) in nuclear norm, analogous to SGD's optimal rate when nuclear norm scales as Theta(sqrt(m+n)) times Frobenius norm."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"AdamW-style Shampoo unifies one-sided and two-sided preconditioning to achieve an SGD-like convergence rate in nuclear norm."}],"snapshot_sha256":"a4bdbdb09ed1cffa0deb2ab91dc0a7f392349d920126dfc64954e4f5c4e71b65"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"87a337bb60f7c45b5faa450549507a141a5309e4028a2021a67d78451d971949"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.07326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies the AdamW-style Shampoo optimizer, an effective implementation of classical Shampoo that notably won the external tuning track of the AlgoPerf neural network training algorithm competition. Our analysis unifies one-sided and two-sided preconditioning and establishes the convergence rate $\\frac{1}{K}\\sum_{k=1}^K E\\left[\\|\\nabla f(X_k)\\|_*\\right]\\leq O(\\frac{\\sqrt{m+n}C}{K^{1/4}})$ measured by nuclear norm, where $K$ represents the iteration number, $(m,n)$ denotes the size of matrix parameters, and $C$ matches the constant in the optimal convergence rate of SGD. Theoretically","authors_text":"Huan Li, Yiming Dong, Zhouchen Lin","cross_cats":["cs.LG"],"headline":"AdamW-style Shampoo unifies one-sided and two-sided preconditioning to achieve an SGD-like convergence rate in nuclear norm.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-01-12T08:51:03Z","title":"Convergence Rate Analysis of the AdamW-Style Shampoo: Unifying One-Sided and Two-Sided Preconditioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.07326","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T15:33:28.762115Z","id":"d8814ebf-967b-453e-86ad-1bf2f7e16741","model_set":{"reader":"grok-4.3"},"one_line_summary":"AdamW-style Shampoo unifies one- and two-sided preconditioning and achieves convergence rate O(sqrt(m+n) C / K^{1/4}) in nuclear norm, analogous to SGD's optimal rate when nuclear norm scales as Theta(sqrt(m+n)) times Frobenius norm.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"AdamW-style Shampoo unifies one-sided and two-sided preconditioning to achieve an SGD-like convergence rate in nuclear norm.","strongest_claim":"Our analysis unifies one-sided and two-sided preconditioning and establishes the convergence rate 1/K sum_{k=1}^K E[||nabla f(X_k)||_*] <= O(sqrt(m+n) C / K^{1/4}) measured by nuclear norm.","weakest_assumption":"The derivation relies on standard stochastic-optimization assumptions (smoothness, bounded variance or similar) together with the specific form of the AdamW-style preconditioner; the abstract does not list the precise conditions under which the nuclear-norm bound holds."}},"verdict_id":"d8814ebf-967b-453e-86ad-1bf2f7e16741"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:981e7feb6554b40559cd153fcaa663b4ef61301c696c325f2e5ab7ba5ab9f912","target":"record","created_at":"2026-05-26T02:04:02Z","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":"acf196fa014f2c358fe7b80ca3cdbbfc37e6d17a27e0372a5eb3f25ab39b88c6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-01-12T08:51:03Z","title_canon_sha256":"69c3092ca2f2c829965d7a48a0aa50ef530a4f53d345f7b0a9bedd43b5260bb4"},"schema_version":"1.0","source":{"id":"2601.07326","kind":"arxiv","version":3}},"canonical_sha256":"460f630b65aa26d49c9a3a94f75e65bebbd95699c8da782d92748a3c0e6658d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"460f630b65aa26d49c9a3a94f75e65bebbd95699c8da782d92748a3c0e6658d6","first_computed_at":"2026-05-26T02:04:02.946717Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:02.946717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bWxfp5o0HKHlb3dNAIKYBnY85Ipmo7TbLHTt/GtGV+YgrmNKLCqVsAxgTzKFxJ04fKwjyopagb751T3cCnhYAQ==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:02.947633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.07326","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:981e7feb6554b40559cd153fcaa663b4ef61301c696c325f2e5ab7ba5ab9f912","sha256:f55ef13fca0808fef63eb47196d46ec7d632379b779750036d1873e729889ef6"],"state_sha256":"594c13e868418bf7e1daf942fb2affae9fdd07d379c9abe34b244f9aee1c107f"}