{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IYHWGC3FVITNJHE2HKKPOXTFX2","short_pith_number":"pith:IYHWGC3F","canonical_record":{"source":{"id":"2601.07326","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-01-12T08:51:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"69c3092ca2f2c829965d7a48a0aa50ef530a4f53d345f7b0a9bedd43b5260bb4","abstract_canon_sha256":"acf196fa014f2c358fe7b80ca3cdbbfc37e6d17a27e0372a5eb3f25ab39b88c6"},"schema_version":"1.0"},"canonical_sha256":"460f630b65aa26d49c9a3a94f75e65bebbd95699c8da782d92748a3c0e6658d6","source":{"kind":"arxiv","id":"2601.07326","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IYHWGC3FVITNJHE2HKKPOXTFX2","target":"record","payload":{"canonical_record":{"source":{"id":"2601.07326","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-01-12T08:51:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"69c3092ca2f2c829965d7a48a0aa50ef530a4f53d345f7b0a9bedd43b5260bb4","abstract_canon_sha256":"acf196fa014f2c358fe7b80ca3cdbbfc37e6d17a27e0372a5eb3f25ab39b88c6"},"schema_version":"1.0"},"canonical_sha256":"460f630b65aa26d49c9a3a94f75e65bebbd95699c8da782d92748a3c0e6658d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:02.947633Z","signature_b64":"bWxfp5o0HKHlb3dNAIKYBnY85Ipmo7TbLHTt/GtGV+YgrmNKLCqVsAxgTzKFxJ04fKwjyopagb751T3cCnhYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"460f630b65aa26d49c9a3a94f75e65bebbd95699c8da782d92748a3c0e6658d6","last_reissued_at":"2026-05-26T02:04:02.946717Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:02.946717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.07326","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4yYNJJz5bAf1kKiHgcikjq2YxwfFtu/FirLxOsvWZEb53XadTjgqwiSmFXHx2rFh4lFWQh6zvUkBy5PRFrofCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T09:09:47.333023Z"},"content_sha256":"981e7feb6554b40559cd153fcaa663b4ef61301c696c325f2e5ab7ba5ab9f912","schema_version":"1.0","event_id":"sha256:981e7feb6554b40559cd153fcaa663b4ef61301c696c325f2e5ab7ba5ab9f912"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IYHWGC3FVITNJHE2HKKPOXTFX2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convergence Rate Analysis of the AdamW-Style Shampoo: Unifying One-Sided and Two-Sided Preconditioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"AdamW-style Shampoo unifies one-sided and two-sided preconditioning to achieve an SGD-like convergence rate in nuclear norm.","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Huan Li, Yiming Dong, Zhouchen Lin","submitted_at":"2026-01-12T08:51:03Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AdamW-style Shampoo unifies one-sided and two-sided preconditioning to achieve an SGD-like convergence rate in nuclear norm.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a4bdbdb09ed1cffa0deb2ab91dc0a7f392349d920126dfc64954e4f5c4e71b65"},"source":{"id":"2601.07326","kind":"arxiv","version":3},"verdict":{"id":"d8814ebf-967b-453e-86ad-1bf2f7e16741","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T15:33:28.762115Z","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.","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","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.","pith_extraction_headline":"AdamW-style Shampoo unifies one-sided and two-sided preconditioning to achieve an SGD-like convergence rate in nuclear norm."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.07326/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"87a337bb60f7c45b5faa450549507a141a5309e4028a2021a67d78451d971949"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"d8814ebf-967b-453e-86ad-1bf2f7e16741"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LCfT26sGJAzsWqhJlbD0S91gikUf3ADryYLknFBLVlXye+AagU3qxwfolgVBAn6e2pREVo27Xa4zJg3UfG5pBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T09:09:47.333963Z"},"content_sha256":"f55ef13fca0808fef63eb47196d46ec7d632379b779750036d1873e729889ef6","schema_version":"1.0","event_id":"sha256:f55ef13fca0808fef63eb47196d46ec7d632379b779750036d1873e729889ef6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IYHWGC3FVITNJHE2HKKPOXTFX2/bundle.json","state_url":"https://pith.science/pith/IYHWGC3FVITNJHE2HKKPOXTFX2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IYHWGC3FVITNJHE2HKKPOXTFX2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-06T09:09:47Z","links":{"resolver":"https://pith.science/pith/IYHWGC3FVITNJHE2HKKPOXTFX2","bundle":"https://pith.science/pith/IYHWGC3FVITNJHE2HKKPOXTFX2/bundle.json","state":"https://pith.science/pith/IYHWGC3FVITNJHE2HKKPOXTFX2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IYHWGC3FVITNJHE2HKKPOXTFX2/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wqMEtsG3JL5iM/HPMCcDmeJ08lJGcOuiOgZ7+8er80+fT43e25ent0DvbntHzZi3etzzgrio1ldUpmFGJJVtDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T09:09:47.337833Z","bundle_sha256":"b8ac6cb1f46d79e3677cad87c54e47abcd9e1518e70ace97de62c35fce2519a4"}}