{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X54CEM5BUBFPSMUZ5UVO62O6TP","short_pith_number":"pith:X54CEM5B","schema_version":"1.0","canonical_sha256":"bf782233a1a04af93299ed2aef69de9bd0d42771e2f2365cfab08dc1bcb6214e","source":{"kind":"arxiv","id":"2509.08911","version":1},"attestation_state":"computed","paper":{"title":"Instance-Optimal Matrix Multiplicative Weight Update and Its Quantum Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DS","quant-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tongyang Li, Weiyuan Gong, Xinzhao Wang, Zhiyu Zhang","submitted_at":"2025-09-10T18:15:41Z","abstract_excerpt":"The Matrix Multiplicative Weight Update (MMWU) is a seminal online learning algorithm with numerous applications. Applied to the matrix version of the Learning from Expert Advice (LEA) problem on the $d$-dimensional spectraplex, it is well known that MMWU achieves the minimax-optimal regret bound of $O(\\sqrt{T\\log d})$, where $T$ is the time horizon. In this paper, we present an improved algorithm achieving the instance-optimal regret bound of $O(\\sqrt{T\\cdot S(X||d^{-1}I_d)})$, where $X$ is the comparator in the regret, $I_d$ is the identity matrix, and $S(\\cdot||\\cdot)$ denotes the quantum r"},"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":"2509.08911","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T18:15:41Z","cross_cats_sorted":["cs.AI","cs.DS","quant-ph","stat.ML"],"title_canon_sha256":"06999add61dec2bcc10d62e4ab325830801fcb0212a41ca8809e65cb3972dd32","abstract_canon_sha256":"b35915a6de358ad76f0e7f4827ee8e7a645eabd1195d6943f87e43df0af40e9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:39.184200Z","signature_b64":"KMTybwq/hf7VhVgzCpt8dQfZljcAhF7c/OcRIj0tg58cqEao+Dj82HgiXeXmoZqu+hN7JGCYu3YuWQB6s7E6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf782233a1a04af93299ed2aef69de9bd0d42771e2f2365cfab08dc1bcb6214e","last_reissued_at":"2026-07-05T12:08:39.183712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:39.183712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instance-Optimal Matrix Multiplicative Weight Update and Its Quantum Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DS","quant-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tongyang Li, Weiyuan Gong, Xinzhao Wang, Zhiyu Zhang","submitted_at":"2025-09-10T18:15:41Z","abstract_excerpt":"The Matrix Multiplicative Weight Update (MMWU) is a seminal online learning algorithm with numerous applications. Applied to the matrix version of the Learning from Expert Advice (LEA) problem on the $d$-dimensional spectraplex, it is well known that MMWU achieves the minimax-optimal regret bound of $O(\\sqrt{T\\log d})$, where $T$ is the time horizon. In this paper, we present an improved algorithm achieving the instance-optimal regret bound of $O(\\sqrt{T\\cdot S(X||d^{-1}I_d)})$, where $X$ is the comparator in the regret, $I_d$ is the identity matrix, and $S(\\cdot||\\cdot)$ denotes the quantum r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08911","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.08911/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":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":"2509.08911","created_at":"2026-07-05T12:08:39.183769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08911v1","created_at":"2026-07-05T12:08:39.183769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08911","created_at":"2026-07-05T12:08:39.183769+00:00"},{"alias_kind":"pith_short_12","alias_value":"X54CEM5BUBFP","created_at":"2026-07-05T12:08:39.183769+00:00"},{"alias_kind":"pith_short_16","alias_value":"X54CEM5BUBFPSMUZ","created_at":"2026-07-05T12:08:39.183769+00:00"},{"alias_kind":"pith_short_8","alias_value":"X54CEM5B","created_at":"2026-07-05T12:08:39.183769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02655","citing_title":"Coherent Swap Regret and Channel-Proof Learning","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X54CEM5BUBFPSMUZ5UVO62O6TP","json":"https://pith.science/pith/X54CEM5BUBFPSMUZ5UVO62O6TP.json","graph_json":"https://pith.science/api/pith-number/X54CEM5BUBFPSMUZ5UVO62O6TP/graph.json","events_json":"https://pith.science/api/pith-number/X54CEM5BUBFPSMUZ5UVO62O6TP/events.json","paper":"https://pith.science/paper/X54CEM5B"},"agent_actions":{"view_html":"https://pith.science/pith/X54CEM5BUBFPSMUZ5UVO62O6TP","download_json":"https://pith.science/pith/X54CEM5BUBFPSMUZ5UVO62O6TP.json","view_paper":"https://pith.science/paper/X54CEM5B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08911&json=true","fetch_graph":"https://pith.science/api/pith-number/X54CEM5BUBFPSMUZ5UVO62O6TP/graph.json","fetch_events":"https://pith.science/api/pith-number/X54CEM5BUBFPSMUZ5UVO62O6TP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X54CEM5BUBFPSMUZ5UVO62O6TP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X54CEM5BUBFPSMUZ5UVO62O6TP/action/storage_attestation","attest_author":"https://pith.science/pith/X54CEM5BUBFPSMUZ5UVO62O6TP/action/author_attestation","sign_citation":"https://pith.science/pith/X54CEM5BUBFPSMUZ5UVO62O6TP/action/citation_signature","submit_replication":"https://pith.science/pith/X54CEM5BUBFPSMUZ5UVO62O6TP/action/replication_record"}},"created_at":"2026-07-05T12:08:39.183769+00:00","updated_at":"2026-07-05T12:08:39.183769+00:00"}