{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W6GFA554ZUY7UE2ZCWT6LC3L2S","short_pith_number":"pith:W6GFA554","schema_version":"1.0","canonical_sha256":"b78c5077bccd31fa135915a7e58b6bd49d6b8863646b79abcfd4789d9e64827b","source":{"kind":"arxiv","id":"2408.09655","version":2},"attestation_state":"computed","paper":{"title":"Contextual Bandits for Unbounded Context Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Li Shen, Puning Zhao, Qixin Zhang, Rongfei Fan, Shaowei Wang, Tianhang Zheng, Zong Ke","submitted_at":"2024-08-19T02:30:37Z","abstract_excerpt":"Nonparametric contextual bandit is an important model of sequential decision making problems. Under $\\alpha$-Tsybakov margin condition, existing research has established a regret bound of $\\tilde{O}\\left(T^{1-\\frac{\\alpha+1}{d+2}}\\right)$ for bounded supports. However, the optimal regret with unbounded contexts has not been analyzed. The challenge of solving contextual bandit problems with unbounded support is to achieve both exploration-exploitation tradeoff and bias-variance tradeoff simultaneously. In this paper, we solve the nonparametric contextual bandit problem with unbounded contexts. "},"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":"2408.09655","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T02:30:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d3f19804a65035063cc384ba289b0dd1e7f27738008d4c1ed537f8f6dcfffa29","abstract_canon_sha256":"8649c05f6bbe341afd0bb46bd676ea448474491d69c79d44ab857c21d781a570"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:59.498547Z","signature_b64":"ByUuFhE5CvrRVy5HT1EFnd8axPDZvflDsuYcAvNhZ6YZJlwR9VmmPiHSgJ9FInkFVsaaDP1ZUKx2ywVrEcxSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b78c5077bccd31fa135915a7e58b6bd49d6b8863646b79abcfd4789d9e64827b","last_reissued_at":"2026-07-05T10:59:59.498023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:59.498023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextual Bandits for Unbounded Context Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Li Shen, Puning Zhao, Qixin Zhang, Rongfei Fan, Shaowei Wang, Tianhang Zheng, Zong Ke","submitted_at":"2024-08-19T02:30:37Z","abstract_excerpt":"Nonparametric contextual bandit is an important model of sequential decision making problems. Under $\\alpha$-Tsybakov margin condition, existing research has established a regret bound of $\\tilde{O}\\left(T^{1-\\frac{\\alpha+1}{d+2}}\\right)$ for bounded supports. However, the optimal regret with unbounded contexts has not been analyzed. The challenge of solving contextual bandit problems with unbounded support is to achieve both exploration-exploitation tradeoff and bias-variance tradeoff simultaneously. In this paper, we solve the nonparametric contextual bandit problem with unbounded contexts. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09655","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/2408.09655/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":"2408.09655","created_at":"2026-07-05T10:59:59.498090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09655v2","created_at":"2026-07-05T10:59:59.498090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09655","created_at":"2026-07-05T10:59:59.498090+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6GFA554ZUY7","created_at":"2026-07-05T10:59:59.498090+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6GFA554ZUY7UE2Z","created_at":"2026-07-05T10:59:59.498090+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6GFA554","created_at":"2026-07-05T10:59:59.498090+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11421","citing_title":"Deep Learning Model Acceleration and Optimization Strategies for Real-Time Recommendation Systems","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6GFA554ZUY7UE2ZCWT6LC3L2S","json":"https://pith.science/pith/W6GFA554ZUY7UE2ZCWT6LC3L2S.json","graph_json":"https://pith.science/api/pith-number/W6GFA554ZUY7UE2ZCWT6LC3L2S/graph.json","events_json":"https://pith.science/api/pith-number/W6GFA554ZUY7UE2ZCWT6LC3L2S/events.json","paper":"https://pith.science/paper/W6GFA554"},"agent_actions":{"view_html":"https://pith.science/pith/W6GFA554ZUY7UE2ZCWT6LC3L2S","download_json":"https://pith.science/pith/W6GFA554ZUY7UE2ZCWT6LC3L2S.json","view_paper":"https://pith.science/paper/W6GFA554","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09655&json=true","fetch_graph":"https://pith.science/api/pith-number/W6GFA554ZUY7UE2ZCWT6LC3L2S/graph.json","fetch_events":"https://pith.science/api/pith-number/W6GFA554ZUY7UE2ZCWT6LC3L2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6GFA554ZUY7UE2ZCWT6LC3L2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6GFA554ZUY7UE2ZCWT6LC3L2S/action/storage_attestation","attest_author":"https://pith.science/pith/W6GFA554ZUY7UE2ZCWT6LC3L2S/action/author_attestation","sign_citation":"https://pith.science/pith/W6GFA554ZUY7UE2ZCWT6LC3L2S/action/citation_signature","submit_replication":"https://pith.science/pith/W6GFA554ZUY7UE2ZCWT6LC3L2S/action/replication_record"}},"created_at":"2026-07-05T10:59:59.498090+00:00","updated_at":"2026-07-05T10:59:59.498090+00:00"}