{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FRKL7WXZUCWHZWGE4UPY5KZUNC","short_pith_number":"pith:FRKL7WXZ","schema_version":"1.0","canonical_sha256":"2c54bfdaf9a0ac7cd8c4e51f8eab346888500fdab94792250dacda1287355b2f","source":{"kind":"arxiv","id":"1802.09568","version":2},"attestation_state":"computed","paper":{"title":"Shampoo: Preconditioned Stochastic Tensor Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tomer Koren, Vineet Gupta, Yoram Singer","submitted_at":"2018-02-26T19:36:41Z","abstract_excerpt":"Preconditioned gradient methods are among the most general and powerful tools in optimization. However, preconditioning requires storing and manipulating prohibitively large matrices. We describe and analyze a new structure-aware preconditioning algorithm, called Shampoo, for stochastic optimization over tensor spaces. Shampoo maintains a set of preconditioning matrices, each of which operates on a single dimension, contracting over the remaining dimensions. We establish convergence guarantees in the stochastic convex setting, the proof of which builds upon matrix trace inequalities. Our exper"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1802.09568","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T19:36:41Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"9d50fc2a10feb8f5090c91c46c1056185ab329421f23306b747081ea7d7bf64c","abstract_canon_sha256":"3e270062d66046aa89db032b669be42395574687c0b1b45eb6104bccfe37415e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:08.497254Z","signature_b64":"9+rkFtr25ryEklApPbMNPlC+576igtplH9SFJSXLTJueJtG2vIq0zUYrVfRowsn1IeQp+sRJMHH4gftFOzS6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c54bfdaf9a0ac7cd8c4e51f8eab346888500fdab94792250dacda1287355b2f","last_reissued_at":"2026-05-18T00:22:08.496721Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:08.496721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shampoo: Preconditioned Stochastic Tensor Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tomer Koren, Vineet Gupta, Yoram Singer","submitted_at":"2018-02-26T19:36:41Z","abstract_excerpt":"Preconditioned gradient methods are among the most general and powerful tools in optimization. However, preconditioning requires storing and manipulating prohibitively large matrices. We describe and analyze a new structure-aware preconditioning algorithm, called Shampoo, for stochastic optimization over tensor spaces. Shampoo maintains a set of preconditioning matrices, each of which operates on a single dimension, contracting over the remaining dimensions. We establish convergence guarantees in the stochastic convex setting, the proof of which builds upon matrix trace inequalities. Our exper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09568","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1802.09568","created_at":"2026-05-18T00:22:08.496790+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.09568v2","created_at":"2026-05-18T00:22:08.496790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09568","created_at":"2026-05-18T00:22:08.496790+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRKL7WXZUCWH","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRKL7WXZUCWHZWGE","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRKL7WXZ","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.23061","citing_title":"Anytime Training with Schedule-Free Spectral Optimization","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"1907.05019","citing_title":"Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16184","citing_title":"Runtime-Orchestrated Second-Order Optimization for Scalable LLM Training","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09331","citing_title":"Dimension-Free Saddle-Point Escape in Muon","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FRKL7WXZUCWHZWGE4UPY5KZUNC","json":"https://pith.science/pith/FRKL7WXZUCWHZWGE4UPY5KZUNC.json","graph_json":"https://pith.science/api/pith-number/FRKL7WXZUCWHZWGE4UPY5KZUNC/graph.json","events_json":"https://pith.science/api/pith-number/FRKL7WXZUCWHZWGE4UPY5KZUNC/events.json","paper":"https://pith.science/paper/FRKL7WXZ"},"agent_actions":{"view_html":"https://pith.science/pith/FRKL7WXZUCWHZWGE4UPY5KZUNC","download_json":"https://pith.science/pith/FRKL7WXZUCWHZWGE4UPY5KZUNC.json","view_paper":"https://pith.science/paper/FRKL7WXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.09568&json=true","fetch_graph":"https://pith.science/api/pith-number/FRKL7WXZUCWHZWGE4UPY5KZUNC/graph.json","fetch_events":"https://pith.science/api/pith-number/FRKL7WXZUCWHZWGE4UPY5KZUNC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRKL7WXZUCWHZWGE4UPY5KZUNC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRKL7WXZUCWHZWGE4UPY5KZUNC/action/storage_attestation","attest_author":"https://pith.science/pith/FRKL7WXZUCWHZWGE4UPY5KZUNC/action/author_attestation","sign_citation":"https://pith.science/pith/FRKL7WXZUCWHZWGE4UPY5KZUNC/action/citation_signature","submit_replication":"https://pith.science/pith/FRKL7WXZUCWHZWGE4UPY5KZUNC/action/replication_record"}},"created_at":"2026-05-18T00:22:08.496790+00:00","updated_at":"2026-05-18T00:22:08.496790+00:00"}