{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:P3CDKY6HFRHUDCPOZ46YYPVQDJ","short_pith_number":"pith:P3CDKY6H","schema_version":"1.0","canonical_sha256":"7ec43563c72c4f4189eecf3d8c3eb01a5bf1313ad88017b295e3903e093e49c6","source":{"kind":"arxiv","id":"1502.06398","version":1},"attestation_state":"computed","paper":{"title":"Bandit Convex Optimization: sqrt{T} Regret in One Dimension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Ofer Dekel, S\\'ebastien Bubeck, Tomer Koren, Yuval Peres","submitted_at":"2015-02-23T11:54:30Z","abstract_excerpt":"We analyze the minimax regret of the adversarial bandit convex optimization problem. Focusing on the one-dimensional case, we prove that the minimax regret is $\\widetilde\\Theta(\\sqrt{T})$ and partially resolve a decade-old open problem. Our analysis is non-constructive, as we do not present a concrete algorithm that attains this regret rate. Instead, we use minimax duality to reduce the problem to a Bayesian setting, where the convex loss functions are drawn from a worst-case distribution, and then we solve the Bayesian version of the problem with a variant of Thompson Sampling. Our analysis f"},"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":"1502.06398","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-23T11:54:30Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"d327e519121ec6e0eb4490d55ad8c63e438c8d3aa8e0d6c306d100e226c942a0","abstract_canon_sha256":"ea4e2f7f4908cab0b6cd46d11f7c3b0495a84a3269a6c0668df81dc2502ab491"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:26:37.374769Z","signature_b64":"WjlnvvgO57p9tUpZFBVaDZz4BFjWJFhlzlxaU2owtwB7f7Y1vqaBP38iVf6ljQnfYb/qQ/arAVsayY/MC6sECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ec43563c72c4f4189eecf3d8c3eb01a5bf1313ad88017b295e3903e093e49c6","last_reissued_at":"2026-05-18T02:26:37.374178Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:26:37.374178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bandit Convex Optimization: sqrt{T} Regret in One Dimension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Ofer Dekel, S\\'ebastien Bubeck, Tomer Koren, Yuval Peres","submitted_at":"2015-02-23T11:54:30Z","abstract_excerpt":"We analyze the minimax regret of the adversarial bandit convex optimization problem. Focusing on the one-dimensional case, we prove that the minimax regret is $\\widetilde\\Theta(\\sqrt{T})$ and partially resolve a decade-old open problem. Our analysis is non-constructive, as we do not present a concrete algorithm that attains this regret rate. Instead, we use minimax duality to reduce the problem to a Bayesian setting, where the convex loss functions are drawn from a worst-case distribution, and then we solve the Bayesian version of the problem with a variant of Thompson Sampling. Our analysis f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.06398","kind":"arxiv","version":1},"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":"1502.06398","created_at":"2026-05-18T02:26:37.374249+00:00"},{"alias_kind":"arxiv_version","alias_value":"1502.06398v1","created_at":"2026-05-18T02:26:37.374249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.06398","created_at":"2026-05-18T02:26:37.374249+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3CDKY6HFRHU","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3CDKY6HFRHUDCPO","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3CDKY6H","created_at":"2026-05-18T12:29:34.919912+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/P3CDKY6HFRHUDCPOZ46YYPVQDJ","json":"https://pith.science/pith/P3CDKY6HFRHUDCPOZ46YYPVQDJ.json","graph_json":"https://pith.science/api/pith-number/P3CDKY6HFRHUDCPOZ46YYPVQDJ/graph.json","events_json":"https://pith.science/api/pith-number/P3CDKY6HFRHUDCPOZ46YYPVQDJ/events.json","paper":"https://pith.science/paper/P3CDKY6H"},"agent_actions":{"view_html":"https://pith.science/pith/P3CDKY6HFRHUDCPOZ46YYPVQDJ","download_json":"https://pith.science/pith/P3CDKY6HFRHUDCPOZ46YYPVQDJ.json","view_paper":"https://pith.science/paper/P3CDKY6H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1502.06398&json=true","fetch_graph":"https://pith.science/api/pith-number/P3CDKY6HFRHUDCPOZ46YYPVQDJ/graph.json","fetch_events":"https://pith.science/api/pith-number/P3CDKY6HFRHUDCPOZ46YYPVQDJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3CDKY6HFRHUDCPOZ46YYPVQDJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3CDKY6HFRHUDCPOZ46YYPVQDJ/action/storage_attestation","attest_author":"https://pith.science/pith/P3CDKY6HFRHUDCPOZ46YYPVQDJ/action/author_attestation","sign_citation":"https://pith.science/pith/P3CDKY6HFRHUDCPOZ46YYPVQDJ/action/citation_signature","submit_replication":"https://pith.science/pith/P3CDKY6HFRHUDCPOZ46YYPVQDJ/action/replication_record"}},"created_at":"2026-05-18T02:26:37.374249+00:00","updated_at":"2026-05-18T02:26:37.374249+00:00"}