{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XG6ZY5JYFV44DY5XFPPT5MMZ4W","short_pith_number":"pith:XG6ZY5JY","schema_version":"1.0","canonical_sha256":"b9bd9c75382d79c1e3b72bdf3eb199e5994058d3659289da601886c902856f9c","source":{"kind":"arxiv","id":"2402.09152","version":2},"attestation_state":"computed","paper":{"title":"Improved Regret for Bandit Convex Optimization with Delayed Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Yao, Lijun Zhang, Mingli Song, Yuanyu Wan","submitted_at":"2024-02-14T13:08:26Z","abstract_excerpt":"We investigate bandit convex optimization (BCO) with delayed feedback, where only the loss value of the action is revealed under an arbitrary delay. Let $n,T,\\bar{d}$ denote the dimensionality, time horizon, and average delay, respectively. Previous studies have achieved an $O(\\sqrt{n}T^{3/4}+(n\\bar{d})^{1/3}T^{2/3})$ regret bound for this problem, whose delay-independent part matches the regret of the classical non-delayed bandit gradient descent algorithm. However, there is a large gap between its delay-dependent part, i.e., $O((n\\bar{d})^{1/3}T^{2/3})$, and an existing $\\Omega(\\sqrt{\\bar{d}"},"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":"2402.09152","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-14T13:08:26Z","cross_cats_sorted":[],"title_canon_sha256":"6358f87b4b08c2e40a09ee3aed748a35c29ac2706f6698e133d6034017c3fab7","abstract_canon_sha256":"c1f38c7fd3d74d03e028bf919dd5baa6e097175298375a0ca9da02de95367e63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:41.855979Z","signature_b64":"j8KBD9rbpobPAzz8AJKF/B4GNmFtNZwYSWw7xg9GQpkaefSDsoREFw6XTbAa4FMFonra8mwI400TDIr0O8e1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9bd9c75382d79c1e3b72bdf3eb199e5994058d3659289da601886c902856f9c","last_reissued_at":"2026-07-05T08:35:41.855550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:41.855550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Regret for Bandit Convex Optimization with Delayed Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Yao, Lijun Zhang, Mingli Song, Yuanyu Wan","submitted_at":"2024-02-14T13:08:26Z","abstract_excerpt":"We investigate bandit convex optimization (BCO) with delayed feedback, where only the loss value of the action is revealed under an arbitrary delay. Let $n,T,\\bar{d}$ denote the dimensionality, time horizon, and average delay, respectively. Previous studies have achieved an $O(\\sqrt{n}T^{3/4}+(n\\bar{d})^{1/3}T^{2/3})$ regret bound for this problem, whose delay-independent part matches the regret of the classical non-delayed bandit gradient descent algorithm. However, there is a large gap between its delay-dependent part, i.e., $O((n\\bar{d})^{1/3}T^{2/3})$, and an existing $\\Omega(\\sqrt{\\bar{d}"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09152","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/2402.09152/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":"2402.09152","created_at":"2026-07-05T08:35:41.855604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09152v2","created_at":"2026-07-05T08:35:41.855604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09152","created_at":"2026-07-05T08:35:41.855604+00:00"},{"alias_kind":"pith_short_12","alias_value":"XG6ZY5JYFV44","created_at":"2026-07-05T08:35:41.855604+00:00"},{"alias_kind":"pith_short_16","alias_value":"XG6ZY5JYFV44DY5X","created_at":"2026-07-05T08:35:41.855604+00:00"},{"alias_kind":"pith_short_8","alias_value":"XG6ZY5JY","created_at":"2026-07-05T08:35:41.855604+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00523","citing_title":"Online Nonsubmodular Optimization with Delayed Feedback in the Bandit Setting","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XG6ZY5JYFV44DY5XFPPT5MMZ4W","json":"https://pith.science/pith/XG6ZY5JYFV44DY5XFPPT5MMZ4W.json","graph_json":"https://pith.science/api/pith-number/XG6ZY5JYFV44DY5XFPPT5MMZ4W/graph.json","events_json":"https://pith.science/api/pith-number/XG6ZY5JYFV44DY5XFPPT5MMZ4W/events.json","paper":"https://pith.science/paper/XG6ZY5JY"},"agent_actions":{"view_html":"https://pith.science/pith/XG6ZY5JYFV44DY5XFPPT5MMZ4W","download_json":"https://pith.science/pith/XG6ZY5JYFV44DY5XFPPT5MMZ4W.json","view_paper":"https://pith.science/paper/XG6ZY5JY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09152&json=true","fetch_graph":"https://pith.science/api/pith-number/XG6ZY5JYFV44DY5XFPPT5MMZ4W/graph.json","fetch_events":"https://pith.science/api/pith-number/XG6ZY5JYFV44DY5XFPPT5MMZ4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XG6ZY5JYFV44DY5XFPPT5MMZ4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XG6ZY5JYFV44DY5XFPPT5MMZ4W/action/storage_attestation","attest_author":"https://pith.science/pith/XG6ZY5JYFV44DY5XFPPT5MMZ4W/action/author_attestation","sign_citation":"https://pith.science/pith/XG6ZY5JYFV44DY5XFPPT5MMZ4W/action/citation_signature","submit_replication":"https://pith.science/pith/XG6ZY5JYFV44DY5XFPPT5MMZ4W/action/replication_record"}},"created_at":"2026-07-05T08:35:41.855604+00:00","updated_at":"2026-07-05T08:35:41.855604+00:00"}