{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:Q5G7W55JFDMY3ZPTPFI5TJN7PV","short_pith_number":"pith:Q5G7W55J","schema_version":"1.0","canonical_sha256":"874dfb77a928d98de5f37951d9a5bf7d6626a43f89afa1594ac783cf33b6abd4","source":{"kind":"arxiv","id":"1202.3079","version":1},"attestation_state":"computed","paper":{"title":"Towards minimax policies for online linear optimization with bandit feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nicol\\`o Cesa-Bianchi, S\\'ebastien Bubeck, Sham M. Kakade","submitted_at":"2012-02-14T16:12:09Z","abstract_excerpt":"We address the online linear optimization problem with bandit feedback. Our contribution is twofold. First, we provide an algorithm (based on exponential weights) with a regret of order $\\sqrt{d n \\log N}$ for any finite action set with $N$ actions, under the assumption that the instantaneous loss is bounded by 1. This shaves off an extraneous $\\sqrt{d}$ factor compared to previous works, and gives a regret bound of order $d \\sqrt{n \\log n}$ for any compact set of actions. Without further assumptions on the action set, this last bound is minimax optimal up to a logarithmic factor. Interestingl"},"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":"1202.3079","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-14T16:12:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7510092912f3e8da99b9b6c4658875be15436cfbe12efe05d29871ce0964e79a","abstract_canon_sha256":"fe475e932834c11fe62096255cfb8a54271b6f2ce3598c054b27d6290885e464"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:02:24.159368Z","signature_b64":"kPERdob3qJmnbbcl3aRebJAcNevSZXlR22oKasn2jUHrA9OyKyWff8iclILl3hLWPmYm8sTRUMUCeliqHBRcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"874dfb77a928d98de5f37951d9a5bf7d6626a43f89afa1594ac783cf33b6abd4","last_reissued_at":"2026-05-18T04:02:24.158562Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:02:24.158562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards minimax policies for online linear optimization with bandit feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nicol\\`o Cesa-Bianchi, S\\'ebastien Bubeck, Sham M. Kakade","submitted_at":"2012-02-14T16:12:09Z","abstract_excerpt":"We address the online linear optimization problem with bandit feedback. Our contribution is twofold. First, we provide an algorithm (based on exponential weights) with a regret of order $\\sqrt{d n \\log N}$ for any finite action set with $N$ actions, under the assumption that the instantaneous loss is bounded by 1. This shaves off an extraneous $\\sqrt{d}$ factor compared to previous works, and gives a regret bound of order $d \\sqrt{n \\log n}$ for any compact set of actions. Without further assumptions on the action set, this last bound is minimax optimal up to a logarithmic factor. Interestingl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.3079","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":"1202.3079","created_at":"2026-05-18T04:02:24.158707+00:00"},{"alias_kind":"arxiv_version","alias_value":"1202.3079v1","created_at":"2026-05-18T04:02:24.158707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.3079","created_at":"2026-05-18T04:02:24.158707+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5G7W55JFDMY","created_at":"2026-05-18T12:27:18.751474+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5G7W55JFDMY3ZPT","created_at":"2026-05-18T12:27:18.751474+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5G7W55J","created_at":"2026-05-18T12:27:18.751474+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/Q5G7W55JFDMY3ZPTPFI5TJN7PV","json":"https://pith.science/pith/Q5G7W55JFDMY3ZPTPFI5TJN7PV.json","graph_json":"https://pith.science/api/pith-number/Q5G7W55JFDMY3ZPTPFI5TJN7PV/graph.json","events_json":"https://pith.science/api/pith-number/Q5G7W55JFDMY3ZPTPFI5TJN7PV/events.json","paper":"https://pith.science/paper/Q5G7W55J"},"agent_actions":{"view_html":"https://pith.science/pith/Q5G7W55JFDMY3ZPTPFI5TJN7PV","download_json":"https://pith.science/pith/Q5G7W55JFDMY3ZPTPFI5TJN7PV.json","view_paper":"https://pith.science/paper/Q5G7W55J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1202.3079&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5G7W55JFDMY3ZPTPFI5TJN7PV/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5G7W55JFDMY3ZPTPFI5TJN7PV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5G7W55JFDMY3ZPTPFI5TJN7PV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5G7W55JFDMY3ZPTPFI5TJN7PV/action/storage_attestation","attest_author":"https://pith.science/pith/Q5G7W55JFDMY3ZPTPFI5TJN7PV/action/author_attestation","sign_citation":"https://pith.science/pith/Q5G7W55JFDMY3ZPTPFI5TJN7PV/action/citation_signature","submit_replication":"https://pith.science/pith/Q5G7W55JFDMY3ZPTPFI5TJN7PV/action/replication_record"}},"created_at":"2026-05-18T04:02:24.158707+00:00","updated_at":"2026-05-18T04:02:24.158707+00:00"}