{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DGMJCF2CNLWG3F6AWUKAPWG6PG","short_pith_number":"pith:DGMJCF2C","schema_version":"1.0","canonical_sha256":"19989117426aec6d97c0b51407d8de799a0106a0abfc8ba26b27f5fb888f0fe4","source":{"kind":"arxiv","id":"1802.03692","version":4},"attestation_state":"computed","paper":{"title":"Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary Bandit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Branislav Kveton, Yang Cao, Yao Xie, Zheng Wen","submitted_at":"2018-02-11T04:57:28Z","abstract_excerpt":"Multi-armed bandit (MAB) is a class of online learning problems where a learning agent aims to maximize its expected cumulative reward while repeatedly selecting to pull arms with unknown reward distributions. We consider a scenario where the reward distributions may change in a piecewise-stationary fashion at unknown time steps. We show that by incorporating a simple change-detection component with classic UCB algorithms to detect and adapt to changes, our so-called M-UCB algorithm can achieve nearly optimal regret bound on the order of $O(\\sqrt{MKT\\log T})$, where $T$ is the number of time s"},"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":"1802.03692","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-11T04:57:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ee265ffc29a25f6808e78e173aa6da2f38636c0b74357694a2977c82aa4da665","abstract_canon_sha256":"1afc29bf5b2faa83a024a055cedf8008d2679911f3714c617dab128da62650d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:38.824874Z","signature_b64":"gotTzu5i+FBlIGUWEPdt1jOywsh/ec5tLxPv4Gv2Rj5G20m8kbbsgyWEAvpI2K/gsxJ78gKt7MLDtNL7OtJAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19989117426aec6d97c0b51407d8de799a0106a0abfc8ba26b27f5fb888f0fe4","last_reissued_at":"2026-05-17T23:55:38.824200Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:38.824200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary Bandit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Branislav Kveton, Yang Cao, Yao Xie, Zheng Wen","submitted_at":"2018-02-11T04:57:28Z","abstract_excerpt":"Multi-armed bandit (MAB) is a class of online learning problems where a learning agent aims to maximize its expected cumulative reward while repeatedly selecting to pull arms with unknown reward distributions. We consider a scenario where the reward distributions may change in a piecewise-stationary fashion at unknown time steps. We show that by incorporating a simple change-detection component with classic UCB algorithms to detect and adapt to changes, our so-called M-UCB algorithm can achieve nearly optimal regret bound on the order of $O(\\sqrt{MKT\\log T})$, where $T$ is the number of time s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03692","kind":"arxiv","version":4},"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":"1802.03692","created_at":"2026-05-17T23:55:38.824311+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03692v4","created_at":"2026-05-17T23:55:38.824311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03692","created_at":"2026-05-17T23:55:38.824311+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGMJCF2CNLWG","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGMJCF2CNLWG3F6A","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGMJCF2C","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG","json":"https://pith.science/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG.json","graph_json":"https://pith.science/api/pith-number/DGMJCF2CNLWG3F6AWUKAPWG6PG/graph.json","events_json":"https://pith.science/api/pith-number/DGMJCF2CNLWG3F6AWUKAPWG6PG/events.json","paper":"https://pith.science/paper/DGMJCF2C"},"agent_actions":{"view_html":"https://pith.science/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG","download_json":"https://pith.science/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG.json","view_paper":"https://pith.science/paper/DGMJCF2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03692&json=true","fetch_graph":"https://pith.science/api/pith-number/DGMJCF2CNLWG3F6AWUKAPWG6PG/graph.json","fetch_events":"https://pith.science/api/pith-number/DGMJCF2CNLWG3F6AWUKAPWG6PG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG/action/storage_attestation","attest_author":"https://pith.science/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG/action/author_attestation","sign_citation":"https://pith.science/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG/action/citation_signature","submit_replication":"https://pith.science/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG/action/replication_record"}},"created_at":"2026-05-17T23:55:38.824311+00:00","updated_at":"2026-05-17T23:55:38.824311+00:00"}