{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NHBOLIHNWTQP3RVZBCGWBP3532","short_pith_number":"pith:NHBOLIHN","schema_version":"1.0","canonical_sha256":"69c2e5a0edb4e0fdc6b9088d60bf7ddebcd40d10940b51445767e06b8a3a8e4b","source":{"kind":"arxiv","id":"2405.19752","version":2},"attestation_state":"computed","paper":{"title":"Understanding Memory-Regret Trade-Off for Streaming Stochastic Multi-Armed Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chihao Zhang, Yuchen He, Zichun Ye","submitted_at":"2024-05-30T06:56:48Z","abstract_excerpt":"We study the stochastic multi-armed bandit problem in the $P$-pass streaming model. In this problem, the $n$ arms are present in a stream and at most $m<n$ arms and their statistics can be stored in the memory. We give a complete characterization of the optimal regret in terms of $m, n$ and $P$. Specifically, we design an algorithm with $\\tilde O\\left((n-m)^{1+\\frac{2^{P}-2}{2^{P+1}-1}} n^{\\frac{2-2^{P+1}}{2^{P+1}-1}} T^{\\frac{2^P}{2^{P+1}-1}}\\right)$ regret and complement it with an $\\tilde \\Omega\\left((n-m)^{1+\\frac{2^{P}-2}{2^{P+1}-1}} n^{\\frac{2-2^{P+1}}{2^{P+1}-1}} T^{\\frac{2^P}{2^{P+1}-1"},"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":"2405.19752","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T06:56:48Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"0179022faa9c5f1f7ef367d7997c0121fa3ad78b9e5500644ccbb9e8b8660ff5","abstract_canon_sha256":"7169cdba6eeba867264b746491db3b2ca972982ac1d7a2826ef6aa8ee50fc477"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:03.379605Z","signature_b64":"g5UY77rRtQMMwUe3BkUrFrCYUFs+Y8SiONH0gR4TR3p6ags6JITOqZ4iodm/IqaoT753gXHPgD0PQKwI7KN7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69c2e5a0edb4e0fdc6b9088d60bf7ddebcd40d10940b51445767e06b8a3a8e4b","last_reissued_at":"2026-07-05T08:41:03.379140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:03.379140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Memory-Regret Trade-Off for Streaming Stochastic Multi-Armed Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chihao Zhang, Yuchen He, Zichun Ye","submitted_at":"2024-05-30T06:56:48Z","abstract_excerpt":"We study the stochastic multi-armed bandit problem in the $P$-pass streaming model. In this problem, the $n$ arms are present in a stream and at most $m<n$ arms and their statistics can be stored in the memory. We give a complete characterization of the optimal regret in terms of $m, n$ and $P$. Specifically, we design an algorithm with $\\tilde O\\left((n-m)^{1+\\frac{2^{P}-2}{2^{P+1}-1}} n^{\\frac{2-2^{P+1}}{2^{P+1}-1}} T^{\\frac{2^P}{2^{P+1}-1}}\\right)$ regret and complement it with an $\\tilde \\Omega\\left((n-m)^{1+\\frac{2^{P}-2}{2^{P+1}-1}} n^{\\frac{2-2^{P+1}}{2^{P+1}-1}} T^{\\frac{2^P}{2^{P+1}-1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19752","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.19752/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":"2405.19752","created_at":"2026-07-05T08:41:03.379207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19752v2","created_at":"2026-07-05T08:41:03.379207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19752","created_at":"2026-07-05T08:41:03.379207+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHBOLIHNWTQP","created_at":"2026-07-05T08:41:03.379207+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHBOLIHNWTQP3RVZ","created_at":"2026-07-05T08:41:03.379207+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHBOLIHN","created_at":"2026-07-05T08:41:03.379207+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.10546","citing_title":"Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHBOLIHNWTQP3RVZBCGWBP3532","json":"https://pith.science/pith/NHBOLIHNWTQP3RVZBCGWBP3532.json","graph_json":"https://pith.science/api/pith-number/NHBOLIHNWTQP3RVZBCGWBP3532/graph.json","events_json":"https://pith.science/api/pith-number/NHBOLIHNWTQP3RVZBCGWBP3532/events.json","paper":"https://pith.science/paper/NHBOLIHN"},"agent_actions":{"view_html":"https://pith.science/pith/NHBOLIHNWTQP3RVZBCGWBP3532","download_json":"https://pith.science/pith/NHBOLIHNWTQP3RVZBCGWBP3532.json","view_paper":"https://pith.science/paper/NHBOLIHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19752&json=true","fetch_graph":"https://pith.science/api/pith-number/NHBOLIHNWTQP3RVZBCGWBP3532/graph.json","fetch_events":"https://pith.science/api/pith-number/NHBOLIHNWTQP3RVZBCGWBP3532/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHBOLIHNWTQP3RVZBCGWBP3532/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHBOLIHNWTQP3RVZBCGWBP3532/action/storage_attestation","attest_author":"https://pith.science/pith/NHBOLIHNWTQP3RVZBCGWBP3532/action/author_attestation","sign_citation":"https://pith.science/pith/NHBOLIHNWTQP3RVZBCGWBP3532/action/citation_signature","submit_replication":"https://pith.science/pith/NHBOLIHNWTQP3RVZBCGWBP3532/action/replication_record"}},"created_at":"2026-07-05T08:41:03.379207+00:00","updated_at":"2026-07-05T08:41:03.379207+00:00"}