{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6WZ4WSJC5XUBVXDIRHHWOJPO4B","short_pith_number":"pith:6WZ4WSJC","schema_version":"1.0","canonical_sha256":"f5b3cb4922ede81adc6889cf6725eee07fcb360ec0bce08a441bd3b73eb2caf0","source":{"kind":"arxiv","id":"2508.04654","version":3},"attestation_state":"computed","paper":{"title":"Non-Stationary Bandit Convex Optimization: An Optimal Algorithm with Two-Point Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Bo Jiang, Chang He, Shuzhong Zhang","submitted_at":"2025-08-06T17:18:47Z","abstract_excerpt":"This paper studies bandit convex optimization in non-stationary environments with two-point feedback, using dynamic regret as the performance measure. We propose an algorithm based on bandit mirror descent that extends naturally to non-Euclidean settings. Let $T$ be the total number of iterations and $\\mathcal{P}_{T,p}$ the path variation with respect to the $\\ell_p$-norm. In Euclidean space, our algorithm matches the optimal regret bound $\\mathcal{O}(\\sqrt{dT(1+\\mathcal{P}_{T,2})})$, improving upon \\citet{zhao2021bandit} by a factor of $\\mathcal{O}(\\sqrt{d})$. Beyond Euclidean settings, our a"},"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":"2508.04654","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-08-06T17:18:47Z","cross_cats_sorted":[],"title_canon_sha256":"6685eee61f50e1ab28189fa7615d51868406a7c8b8c4864dc139eec3f5fc8298","abstract_canon_sha256":"e38e35517d688dc850d3541230305dcf7e7941dadbde3d205fd96a6a8ea3be4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:03:01.379115Z","signature_b64":"Uq0bJXb7PDV/GeUlxXPdIcFPemhUJbP/p5f5AiyUos95KqJyxWH3CgfffVMDq5n/4/eA/hDdimjEAsAjxkMqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5b3cb4922ede81adc6889cf6725eee07fcb360ec0bce08a441bd3b73eb2caf0","last_reissued_at":"2026-05-26T02:03:01.378123Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:03:01.378123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Stationary Bandit Convex Optimization: An Optimal Algorithm with Two-Point Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Bo Jiang, Chang He, Shuzhong Zhang","submitted_at":"2025-08-06T17:18:47Z","abstract_excerpt":"This paper studies bandit convex optimization in non-stationary environments with two-point feedback, using dynamic regret as the performance measure. We propose an algorithm based on bandit mirror descent that extends naturally to non-Euclidean settings. Let $T$ be the total number of iterations and $\\mathcal{P}_{T,p}$ the path variation with respect to the $\\ell_p$-norm. In Euclidean space, our algorithm matches the optimal regret bound $\\mathcal{O}(\\sqrt{dT(1+\\mathcal{P}_{T,2})})$, improving upon \\citet{zhao2021bandit} by a factor of $\\mathcal{O}(\\sqrt{d})$. Beyond Euclidean settings, our a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04654","kind":"arxiv","version":3},"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/2508.04654/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":"2508.04654","created_at":"2026-05-26T02:03:01.378281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.04654v3","created_at":"2026-05-26T02:03:01.378281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04654","created_at":"2026-05-26T02:03:01.378281+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WZ4WSJC5XUB","created_at":"2026-05-26T02:03:01.378281+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WZ4WSJC5XUBVXDI","created_at":"2026-05-26T02:03:01.378281+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WZ4WSJC","created_at":"2026-05-26T02:03:01.378281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.22191","citing_title":"Bandit Convex Optimization with Gradient Prediction Adaptivity","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6WZ4WSJC5XUBVXDIRHHWOJPO4B","json":"https://pith.science/pith/6WZ4WSJC5XUBVXDIRHHWOJPO4B.json","graph_json":"https://pith.science/api/pith-number/6WZ4WSJC5XUBVXDIRHHWOJPO4B/graph.json","events_json":"https://pith.science/api/pith-number/6WZ4WSJC5XUBVXDIRHHWOJPO4B/events.json","paper":"https://pith.science/paper/6WZ4WSJC"},"agent_actions":{"view_html":"https://pith.science/pith/6WZ4WSJC5XUBVXDIRHHWOJPO4B","download_json":"https://pith.science/pith/6WZ4WSJC5XUBVXDIRHHWOJPO4B.json","view_paper":"https://pith.science/paper/6WZ4WSJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.04654&json=true","fetch_graph":"https://pith.science/api/pith-number/6WZ4WSJC5XUBVXDIRHHWOJPO4B/graph.json","fetch_events":"https://pith.science/api/pith-number/6WZ4WSJC5XUBVXDIRHHWOJPO4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WZ4WSJC5XUBVXDIRHHWOJPO4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WZ4WSJC5XUBVXDIRHHWOJPO4B/action/storage_attestation","attest_author":"https://pith.science/pith/6WZ4WSJC5XUBVXDIRHHWOJPO4B/action/author_attestation","sign_citation":"https://pith.science/pith/6WZ4WSJC5XUBVXDIRHHWOJPO4B/action/citation_signature","submit_replication":"https://pith.science/pith/6WZ4WSJC5XUBVXDIRHHWOJPO4B/action/replication_record"}},"created_at":"2026-05-26T02:03:01.378281+00:00","updated_at":"2026-05-26T02:03:01.378281+00:00"}